AI Agent Engineer (Python)

🏢 Summary: B2B offer for a Voice Agent AI Engineer to design and develop production-grade voice AI agents using LLMs, orchestration frameworks, and real-time pipelines. The role focuses on building reliable, low-latency AI workflows with strong guardrails, evaluation frameworks, and system integrations. You will own end-to-end development of AI agents in a greenfield, AI-native environment. 🗂️ Requirements: Minimum 4 years of commercial experience with Python in production, Strong knowledge of asynchronous programming (asyncio, concurrency, race conditions), Hands-on experience with LLMs (function calling, prompt engineering, error analysis), Experience designing reliable AI systems (guardrails, validation, flow control), Practical experience with Pydantic v2, Experience testing non-deterministic systems (scenario tests, quality metrics), Experience with AI development tools (e.g. Claude Code, Cursor, Copilot) 📃 Skills: Python, asyncio, Concurrency, LLM, Prompting, FunctionCalling, Pydantic, LangGraph, StateGraph, MCP, HTTP, SSE, LiveKit, YAML, Datadog, LangSmith, OpenTelemetry, DeepEval, Docker, Kubernetes, AWS, Whisper, Deepgram, ElevenLabs, Guardrails 🏢 Description: Be in IT to firma rekrutacyjna, wyspecjalizowana w poszukiwaniu Specjalistów z branży technologii informatycznych. Obecnie, dla naszego klienta, poszukujemy osoby na stanowisko: Voice Agent AI Engineer Zakres obowiązków: Projektowanie i rozwój workflow agentów AI w oparciu o LangGraph (StateGraph). Budowa i optymalizacja logiki przejść, stanów oraz ścieżek decyzyjnych. Implementacja guardraili zapewniających poprawne działanie LLM (wykrywanie halucynacji, błędów, braków w sekwencji). Tworzenie narzędzi wywoływanych przez LLM (async Python + Pydantic, retry logic, obsługa błędów). Projektowanie i utrzymanie promptów oraz szablonów YAML z dynamicznym kontekstem. Rozwój i utrzymanie frameworka ewaluacyjnego (testy scenariuszowe, metryki jakości). Integracja systemów poprzez MCP (HTTP/SSE, LiveKit RPC). Monitorowanie i optymalizacja wydajności (Datadog, LangSmith, latency <500 ms p95). Współpraca przy rozwoju voice pipeline (STT, TTS, VAD, echo detection). Debugowanie i poprawa zachowania agentów w środowisku produkcyjnym. Oczekujemy: Minimum 4 lata doświadczenia w Pythonie (środowisko produkcyjne). Bardzo dobra znajomość programowania asynchronicznego (asyncio, race conditions, concurrency). Doświadczenie w pracy z LLM (function calling, prompt engineering, analiza błędów). Umiejętność projektowania systemów zapewniających niezawodność AI (guardrails, walidacja, kontrola przepływu). Praktyczna znajomość Pydantic v2. Doświadczenie w testowaniu systemów niedeterministycznych (testy scenariuszowe, metryki jakości). Doświadczenie w pracy z narzędziami AI (np. Claude Code, Cursor, Copilot). Samodzielność i ownership — prowadzenie rozwiązań od projektu do wdrożenia. Mile widziane: LangGraph lub podobne narzędzia orkiestracji. Doświadczenie z Voice AI (np. Deepgram, Whisper, ElevenLabs). Znajomość MCP (Model Context Protocol). Praca z Datadog, LangSmith, OpenTelemetry. DeepEval lub inne frameworki ewaluacyjne. Docker, Kubernetes, AWS. Doświadczenie w startupie. Oferujemy: Długotrwałą współpracę na zasadach B2B - stawka 60-80 USD/h. Pracę przy zaawansowanym, produkcyjnym systemie agentów AI (voice + LLM + orchestration). Realny wpływ na architekturę i rozwój produktu od podstaw (greenfield). Środowisko AI-native — praca z wykorzystaniem agentów AI w codziennym developmentcie. Dużą autonomię i odpowiedzialność za rozwiązania end-to-end. Możliwość rozwiązywania złożonych problemów (LLM reliability, real-time systems, orchestration). Współpracę z doświadczonym zespołem technologicznym.

🏢 Summary: B2B role for an AI Agent Engineer to design and develop production-grade AI agent workflows using LLMs and orchestration tools, with strong focus on reliability, performance, and voice integration. The position involves building and optimizing agent logic, guardrails, evaluation frameworks, and system integrations in a greenfield AI-native environment. High impact on architecture and end-to-end ownership of AI solutions. 🗂️ Requirements: Minimum 4 years of production experience with Python, Strong experience with asynchronous programming and concurrency (asyncio, race conditions), Hands-on experience with LLMs (function calling, prompt engineering, error analysis), Experience designing AI reliability mechanisms (guardrails, validation, flow control), Practical experience with Pydantic v2, Experience testing non-deterministic systems (scenario testing, quality metrics), Experience with AI development tools (Claude Code, Cursor, Copilot) 📃 Skills: Python, asyncio, LLM, LangGraph, Pydantic, YAML, HTTP, SSE, LiveKit, Datadog, LangSmith, STT, TTS, VAD, Deepgram, Whisper, ElevenLabs, MCP, OpenTelemetry, DeepEval, Docker, Kubernetes, AWS 🏢 Description: Be in IT to firma rekrutacyjna, wyspecjalizowana w poszukiwaniu Specjalistów z branży technologii informatycznych. Obecnie, dla naszego klienta, poszukujemy osoby na stanowisko: AI Agent Engineer Zakres obowiązków: Projektowanie i rozwój workflow agentów AI w oparciu o LangGraph (StateGraph). Budowa i optymalizacja logiki przejść, stanów oraz ścieżek decyzyjnych. Implementacja guardraili zapewniających poprawne działanie LLM (wykrywanie halucynacji, błędów, braków w sekwencji). Tworzenie narzędzi wywoływanych przez LLM (async Python + Pydantic, retry logic, obsługa błędów). Projektowanie i utrzymanie promptów oraz szablonów YAML z dynamicznym kontekstem. Rozwój i utrzymanie frameworka ewaluacyjnego (testy scenariuszowe, metryki jakości). Integracja systemów poprzez MCP (HTTP/SSE, LiveKit RPC). Monitorowanie i optymalizacja wydajności (Datadog, LangSmith, latency <500 ms p95). Współpraca przy rozwoju voice pipeline (STT, TTS, VAD, echo detection). Debugowanie i poprawa zachowania agentów w środowisku produkcyjnym. Oczekujemy: Minimum 4 lata doświadczenia w Pythonie (środowisko produkcyjne). Bardzo dobra znajomość programowania asynchronicznego (asyncio, race conditions, concurrency). Doświadczenie w pracy z LLM (function calling, prompt engineering, analiza błędów). Umiejętność projektowania systemów zapewniających niezawodność AI (guardrails, walidacja, kontrola przepływu). Praktyczna znajomość Pydantic v2. Doświadczenie w testowaniu systemów niedeterministycznych (testy scenariuszowe, metryki jakości). Doświadczenie w pracy z narzędziami AI (np. Claude Code, Cursor, Copilot). Samodzielność i ownership — prowadzenie rozwiązań od projektu do wdrożenia. Mile widziane: LangGraph lub podobne narzędzia orkiestracji. Doświadczenie z Voice AI (np. Deepgram, Whisper, ElevenLabs). Znajomość MCP (Model Context Protocol). Praca z Datadog, LangSmith, OpenTelemetry. DeepEval lub inne frameworki ewaluacyjne. Docker, Kubernetes, AWS. Doświadczenie w startupie. Oferujemy: Długotrwałą współpracę na zasadach B2B - stawka 60-80USD/h. Pracę przy zaawansowanym, produkcyjnym systemie agentów AI (voice + LLM + orchestration). Realny wpływ na architekturę i rozwój produktu od podstaw (greenfield). Środowisko AI-native — praca z wykorzystaniem agentów AI w codziennym developmentcie. Dużą autonomię i odpowiedzialność za rozwiązania end-to-end. Możliwość rozwiązywania złożonych problemów (LLM reliability, real-time systems, orchestration). Współpracę z doświadczonym zespołem technologicznym.

🏢 Summary: The offer is for a Python AI Engineer responsible for building and deploying GenAI agents using agentic frameworks like LangChain and LangGraph on AWS. The role focuses on developing RAG pipelines, integrating vector databases, ensuring reliability and safety, and collaborating within an Agile team. It combines hands-on LLM engineering with cloud deployment, monitoring, and compliance in a healthcare-related context. 🗂️ Requirements: 2+ years of Python development experience with recent focus on LLM or GenAI projects, Hands-on experience with LangChain, LangGraph or similar agent frameworks, Understanding of agentic design patterns (tools, planners, memory), Knowledge of vector databases, embeddings and prompt engineering, Proficiency in Docker, Experience with Git-based CI/CD, Experience with automated testing, Ability to collaborate with technical and non-technical stakeholders 📃 Skills: Python, LangChain, LangGraph, AWS, RAG, LLM, Docker, Git, CI/CD, VectorDB, Embeddings, Prompting, AgenticAI, Logging, Monitoring 🏢 Description: We are seeking a Python AI Engineer with hands-on experience in agentic AI frameworks such as LangChain and LangGraph, who knows how to run GenAI workloads on AWS. Responsibilities Build Python services that power the GenAI agent, using LangChain, LangGraph or similar libraries Creation of retrieval-augmented generation (RAG) flows that pull the right context and streamline LLM responses Run the solution on AWS using containers, serverless or managed AI services Instrument logging, monitoring and guardrails to keep the agent reliable and safe Ensure the ingestion and use of RFP/RFI data follows healthcare data policies Collaboration with product, data science and business teams to make sure the agent solves real problems Document code, APIs and deployment steps so others can maintain and extend the solution Contribute to planning, demos and retros within an Agile team Requirements 2+ years of Python development, with recent focus on LLM or GenAI projects Real-world experience using LangChain, LangGraph or comparable agent frameworks Understanding of agentic design patterns and how to wire tools, planners and memory together Knowledge of vector databases, embeddings and prompt engineering Proficiency in Docker, Git-based CI/CD and automated testing Solid communication skills and the ability to work with technical and non-technical stakeholders Nice to have Familiarity with healthcare payer workflows, especially RFP/RFI processes Experience integrating with CRMs/workflow tools like Salesforce or ServiceNow Exposure to responsible AI, human-in-the-loop review or safety tooling AWS or Python certifications We offer We gather like-minded people: Engineering community of industry professionals Friendly team and enjoyable working environment Flexible schedule and opportunity to work remotely within Poland Chance to work abroad for up to 60 days annually Business-driven relocation opportunities We provide growth opportunities: Outstanding career roadmap Leadership development, career advising, soft skills, and well-being programs Certification (GCP, Azure, AWS) Unlimited access to LinkedIn Learning, Get Abstract, Cloud Guru English classes We cover it all: Stable income (Employment Contract or B2B) Participation in the Employee Stock Purchase Plan Benefits package (health insurance, multisport, shopping vouchers) Strategically located offices featuring entertainment and relaxation zones, table tennis and football, free snacks, fantastic coffee, and more Referral bonuses Corporate, social and well-being events Please, note: The set of bonuses might vary based on the role you apply for – specifics will be discussed with our recruiter during the general interview. We will reach out to selected candidates exclusively. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

🏢 Summary: The offer is for a Python AI Engineer to build and operate agentic GenAI solutions using frameworks like LangChain and LangGraph on AWS. The role focuses on developing RAG pipelines, deploying scalable AI services, and ensuring reliability, safety, and compliance in healthcare-related workflows. You will collaborate within an Agile team to deliver production-ready AI agents integrated with business systems. 🗂️ Requirements: 2+ years of Python development with recent LLM or GenAI focus, Experience with LangChain, LangGraph or similar agent frameworks, Understanding of agentic design patterns (tools, planners, memory), Knowledge of vector databases, embeddings and prompt engineering, Proficiency in Docker, Experience with Git-based CI/CD, Experience with automated testing, Ability to collaborate with technical and non-technical stakeholders 📃 Skills: Python, LangChain, LangGraph, AWS, RAG, LLM, Docker, Git, CI/CD, VectorDB, Embeddings, Prompting, Salesforce, ServiceNow 🏢 Description: We are seeking a Python AI Engineer with hands-on experience in agentic AI frameworks such as LangChain and LangGraph, who knows how to run GenAI workloads on AWS. Responsibilities Build Python services that power the GenAI agent, using LangChain, LangGraph or similar libraries Creation of retrieval-augmented generation (RAG) flows that pull the right context and streamline LLM responses Run the solution on AWS using containers, serverless or managed AI services Instrument logging, monitoring and guardrails to keep the agent reliable and safe Ensure the ingestion and use of RFP/RFI data follows healthcare data policies Collaboration with product, data science and business teams to make sure the agent solves real problems Document code, APIs and deployment steps so others can maintain and extend the solution Contribute to planning, demos and retros within an Agile team Requirements 2+ years of Python development, with recent focus on LLM or GenAI projects Real-world experience using LangChain, LangGraph or comparable agent frameworks Understanding of agentic design patterns and how to wire tools, planners and memory together Knowledge of vector databases, embeddings and prompt engineering Proficiency in Docker, Git-based CI/CD and automated testing Solid communication skills and the ability to work with technical and non-technical stakeholders Nice to have Familiarity with healthcare payer workflows, especially RFP/RFI processes Experience integrating with CRMs/workflow tools like Salesforce or ServiceNow Exposure to responsible AI, human-in-the-loop review or safety tooling AWS or Python certifications We offer We gather like-minded people: Engineering community of industry professionals Friendly team and enjoyable working environment Flexible schedule and opportunity to work remotely within Poland Chance to work abroad for up to 60 days annually Business-driven relocation opportunities We provide growth opportunities: Outstanding career roadmap Leadership development, career advising, soft skills, and well-being programs Certification (GCP, Azure, AWS) Unlimited access to LinkedIn Learning, Get Abstract, Cloud Guru English classes We cover it all: Stable income (Employment Contract or B2B) Participation in the Employee Stock Purchase Plan Benefits package (health insurance, multisport, shopping vouchers) Strategically located offices featuring entertainment and relaxation zones, table tennis and football, free snacks, fantastic coffee, and more Referral bonuses Corporate, social and well-being events Please, note: The set of bonuses might vary based on the role you apply for – specifics will be discussed with our recruiter during the general interview. We will reach out to selected candidates exclusively. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

🏢 Summary: The offer is for a Python AI Engineer to design and deploy GenAI agents using LangChain/LangGraph and AWS. The role focuses on building RAG-based solutions, implementing agentic design patterns, and ensuring reliability, safety, and compliance in healthcare-related workflows. You will work in an Agile team to deliver production-ready AI services with proper documentation, monitoring, and CI/CD practices. 🗂️ Requirements: 2+ years of Python development experience, Hands-on experience with LLM or GenAI projects, Experience with LangChain, LangGraph or similar agent frameworks, Understanding of agentic design patterns, Knowledge of vector databases and embeddings, Knowledge of prompt engineering, Proficiency with Docker, Experience with Git-based CI/CD, Experience with automated testing, Ability to collaborate with technical and non-technical stakeholders 📃 Skills: Python, LangChain, LangGraph, AWS, RAG, LLM, Docker, Git, CI/CD, VectorDB, Embeddings, Prompting, GenAI 🏢 Description: We are seeking a Python AI Engineer with hands-on experience in agentic AI frameworks such as LangChain and LangGraph, who knows how to run GenAI workloads on AWS. Responsibilities Build Python services that power the GenAI agent, using LangChain, LangGraph or similar libraries Creation of retrieval-augmented generation (RAG) flows that pull the right context and streamline LLM responses Run the solution on AWS using containers, serverless or managed AI services Instrument logging, monitoring and guardrails to keep the agent reliable and safe Ensure the ingestion and use of RFP/RFI data follows healthcare data policies Collaboration with product, data science and business teams to make sure the agent solves real problems Document code, APIs and deployment steps so others can maintain and extend the solution Contribute to planning, demos and retros within an Agile team Requirements 2+ years of Python development, with recent focus on LLM or GenAI projects Real-world experience using LangChain, LangGraph or comparable agent frameworks Understanding of agentic design patterns and how to wire tools, planners and memory together Knowledge of vector databases, embeddings and prompt engineering Proficiency in Docker, Git-based CI/CD and automated testing Solid communication skills and the ability to work with technical and non-technical stakeholders Nice to have Familiarity with healthcare payer workflows, especially RFP/RFI processes Experience integrating with CRMs/workflow tools like Salesforce or ServiceNow Exposure to responsible AI, human-in-the-loop review or safety tooling AWS or Python certifications We offer We gather like-minded people: Engineering community of industry professionals Friendly team and enjoyable working environment Flexible schedule and opportunity to work remotely within Poland Chance to work abroad for up to 60 days annually Business-driven relocation opportunities We provide growth opportunities: Outstanding career roadmap Leadership development, career advising, soft skills, and well-being programs Certification (GCP, Azure, AWS) Unlimited access to LinkedIn Learning, Get Abstract, Cloud Guru English classes We cover it all: Stable income (Employment Contract or B2B) Participation in the Employee Stock Purchase Plan Benefits package (health insurance, multisport, shopping vouchers) Strategically located offices featuring entertainment and relaxation zones, table tennis and football, free snacks, fantastic coffee, and more Referral bonuses Corporate, social and well-being events Please, note: The set of bonuses might vary based on the role you apply for – specifics will be discussed with our recruiter during the general interview. We will reach out to selected candidates exclusively. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

🏢 Summary: The offer is for a Python AI Engineer to build and operate agentic GenAI solutions using LangChain/LangGraph on AWS. The role focuses on developing RAG pipelines, deploying scalable services, and ensuring reliability, safety, and healthcare data compliance. You will collaborate in an Agile team to deliver production-ready AI agents integrated with business workflows. 🗂️ Requirements: 2+ years of Python development experience, Recent experience with LLM or GenAI projects, Hands-on experience with LangChain, LangGraph or similar agent frameworks, Understanding of agentic design patterns (tools, planners, memory), Knowledge of vector databases, embeddings and prompt engineering, Proficiency with Docker, Experience with Git-based CI/CD, Experience with automated testing, Ability to collaborate with technical and non-technical stakeholders 📃 Skills: Python, LangChain, LangGraph, AWS, RAG, LLM, Docker, Git, CI/CD, Embeddings, Vector, Prompting, Agile 🏢 Description: We are seeking a Python AI Engineer with hands-on experience in agentic AI frameworks such as LangChain and LangGraph, who knows how to run GenAI workloads on AWS. Responsibilities Build Python services that power the GenAI agent, using LangChain, LangGraph or similar libraries Creation of retrieval-augmented generation (RAG) flows that pull the right context and streamline LLM responses Run the solution on AWS using containers, serverless or managed AI services Instrument logging, monitoring and guardrails to keep the agent reliable and safe Ensure the ingestion and use of RFP/RFI data follows healthcare data policies Collaboration with product, data science and business teams to make sure the agent solves real problems Document code, APIs and deployment steps so others can maintain and extend the solution Contribute to planning, demos and retros within an Agile team Requirements 2+ years of Python development, with recent focus on LLM or GenAI projects Real-world experience using LangChain, LangGraph or comparable agent frameworks Understanding of agentic design patterns and how to wire tools, planners and memory together Knowledge of vector databases, embeddings and prompt engineering Proficiency in Docker, Git-based CI/CD and automated testing Solid communication skills and the ability to work with technical and non-technical stakeholders Nice to have Familiarity with healthcare payer workflows, especially RFP/RFI processes Experience integrating with CRMs/workflow tools like Salesforce or ServiceNow Exposure to responsible AI, human-in-the-loop review or safety tooling AWS or Python certifications We offer We gather like-minded people: Engineering community of industry professionals Friendly team and enjoyable working environment Flexible schedule and opportunity to work remotely within Poland Chance to work abroad for up to 60 days annually Business-driven relocation opportunities We provide growth opportunities: Outstanding career roadmap Leadership development, career advising, soft skills, and well-being programs Certification (GCP, Azure, AWS) Unlimited access to LinkedIn Learning, Get Abstract, Cloud Guru English classes We cover it all: Stable income (Employment Contract or B2B) Participation in the Employee Stock Purchase Plan Benefits package (health insurance, multisport, shopping vouchers) Strategically located offices featuring entertainment and relaxation zones, table tennis and football, free snacks, fantastic coffee, and more Referral bonuses Corporate, social and well-being events Please, note: The set of bonuses might vary based on the role you apply for – specifics will be discussed with our recruiter during the general interview. We will reach out to selected candidates exclusively. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

🏢 Summary: The offer is for a Python AI Engineer to design and build GenAI agents using frameworks like LangChain and LangGraph, deployed on AWS. The role focuses on creating RAG-based solutions, integrating vector databases, and ensuring reliable, secure operation of LLM-powered services. The engineer will work in an Agile team to deliver production-ready AI systems with proper monitoring, documentation, and compliance. 🗂️ Requirements: 2+ years of Python development experience, Experience with LLM or GenAI projects, Hands-on experience with LangChain, LangGraph or similar agent frameworks, Understanding of agentic design patterns, Knowledge of vector databases and embeddings, Experience with prompt engineering, Proficiency in Docker, Experience with Git-based CI/CD, Experience with automated testing, Ability to deploy solutions on AWS 📃 Skills: Python, LangChain, LangGraph, AWS, Docker, Git, CI/CD, LLM, GenAI, RAG, VectorDB, Embeddings, PromptEngineering 🏢 Description: We are seeking a Python AI Engineer with hands-on experience in agentic AI frameworks such as LangChain and LangGraph, who knows how to run GenAI workloads on AWS. Responsibilities Build Python services that power the GenAI agent, using LangChain, LangGraph or similar libraries Creation of retrieval-augmented generation (RAG) flows that pull the right context and streamline LLM responses Run the solution on AWS using containers, serverless or managed AI services Instrument logging, monitoring and guardrails to keep the agent reliable and safe Ensure the ingestion and use of RFP/RFI data follows healthcare data policies Collaboration with product, data science and business teams to make sure the agent solves real problems Document code, APIs and deployment steps so others can maintain and extend the solution Contribute to planning, demos and retros within an Agile team Requirements 2+ years of Python development, with recent focus on LLM or GenAI projects Real-world experience using LangChain, LangGraph or comparable agent frameworks Understanding of agentic design patterns and how to wire tools, planners and memory together Knowledge of vector databases, embeddings and prompt engineering Proficiency in Docker, Git-based CI/CD and automated testing Solid communication skills and the ability to work with technical and non-technical stakeholders Nice to have Familiarity with healthcare payer workflows, especially RFP/RFI processes Experience integrating with CRMs/workflow tools like Salesforce or ServiceNow Exposure to responsible AI, human-in-the-loop review or safety tooling AWS or Python certifications We offer/Benefits We gather like-minded people: Engineering community of industry professionals Friendly team and enjoyable working environment Flexible schedule and opportunity to work remotely within Poland Chance to work abroad for up to 60 days annually Business-driven relocation opportunities We provide growth opportunities: Outstanding career roadmap Leadership development, career advising, soft skills, and well-being programs Certification (GCP, Azure, AWS) Unlimited access to LinkedIn Learning, Get Abstract, Cloud Guru English classes We cover it all: Stable income (Employment Contract or B2B) Participation in the Employee Stock Purchase Plan Benefits package (health insurance, multisport, shopping vouchers) Strategically located offices featuring entertainment and relaxation zones, table tennis and football, free snacks, fantastic coffee, and more Referral bonuses Corporate, social and well-being events Please, note: The set of bonuses might vary based on the role you apply for – specifics will be discussed with our recruiter during the general interview. We will reach out to selected candidates exclusively. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

🏢 Summary: Lead Python AI Engineer role focused on building and leading the development of a GenAI agent that leverages past RFP/RFI data to automate and accelerate responses. The position involves designing agentic AI solutions with LangChain/LangGraph, implementing RAG pipelines, and deploying scalable GenAI workloads on AWS. The engineer will guide the team technically while ensuring reliability, compliance, and production readiness of AI services. 🗂️ Requirements: 5+ years Python development experience, Recent experience with LLM or GenAI projects, At least 1 year leadership experience, Hands-on experience with LangChain or LangGraph, Experience designing agentic AI systems, Experience building RAG pipelines, Expertise in AWS for GenAI workloads, Knowledge of vector databases and embeddings, Experience with prompt engineering, Proficiency with Docker, Experience with Git-based CI/CD, Experience with automated testing, Upper-Intermediate (B2) English proficiency 📃 Skills: Python, LangChain, LangGraph, AWS, LLM, GenAI, RAG, Docker, Git, CI/CD, VectorDB, Embeddings, Prompting, Serverless, Containers 🏢 Description: We are looking for a Lead Python AI Engineer who has hands-on experience with agentic AI frameworks (LangChain, LangGraph, etc.) and knows how to run GenAI workloads on AWS. You will join the team building a GenAI agent that learns from past RFP/RFI responses and helps teams answer new requests faster. Responsibilities Build Python services that power the GenAI agent using LangChain, LangGraph, or similar libraries Create retrieval-augmented generation (RAG) flows that pull the right context and streamline LLM responses Run the solution on AWS using containers, serverless functions, or managed AI services Instrument logging, monitoring, and guardrails to keep the agent reliable and safe Ensure the ingestion and use of RFP/RFI data follows healthcare data policies Collaborate with product, data science, and business teams to make sure the agent solves real problems Document code, APIs, and deployment steps so others can maintain and extend the solution Work within an Agile team and contribute to planning, demos, and retros Lead and technically guide the team Requirements 5+ years of Python development experience, with a recent focus on LLM or GenAI projects At least 1 year of relevant leadership experience Hands-on experience with LangChain, LangGraph, or comparable agent frameworks Expertise in Amazon Web Services for running GenAI workloads Understanding of agentic design patterns and how to wire tools, planners, and memory together Knowledge of vector databases, embeddings, and prompt engineering Proficiency in Docker, Git-based CI/CD, and automated testing Skills in leveraging AI-assisted development tools (e.g., Cursor, GitHub Copilot, Code Interpreter) to accelerate prototyping and code reviews Solid communication skills and the ability to work with technical and non-technical stakeholders English language proficiency at an Upper-Intermediate level (B2) or higher Nice to have Familiarity with healthcare payer workflows, especially RFP/RFI processes Experience integrating with CRMs/workflow tools like Salesforce or ServiceNow Exposure to responsible AI, human-in-the-loop review, or safety tooling AWS or Python certifications We offer/Benefits We gather like-minded people: Engineering community of industry professionals Friendly team and enjoyable working environment Flexible schedule and opportunity to work remotely within Poland Chance to work abroad for up to 60 days annually Business-driven relocation opportunities We provide growth opportunities: Outstanding career roadmap Leadership development, career advising, soft skills, and well-being programs Certification (GCP, Azure, AWS) Unlimited access to LinkedIn Learning, Get Abstract, Cloud Guru English classes We cover it all: Stable income (Employment Contract or B2B) Participation in the Employee Stock Purchase Plan Benefits package (health insurance, multisport, shopping vouchers) Strategically located offices featuring entertainment and relaxation zones, table tennis and football, free snacks, fantastic coffee, and more Referral bonuses Corporate, social and well-being events Please, note: The set of bonuses might vary based on the role you apply for – specifics will be discussed with our recruiter during the general interview. We will reach out to selected candidates exclusively. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

🏢 Summary: Oferta dotyczy roli inżyniera AI/LLM odpowiedzialnego za projektowanie i wdrażanie produkcyjnych systemów opartych na Pythonie oraz zaawansowanych architekturach LLM. Stanowisko obejmuje budowę rozwiązań RAG, orkiestrację agentów oraz przygotowanie pipeline’ów danych pod modele językowe. Rola wymaga pracy z wektorowymi bazami danych oraz zapewnienia jakości poprzez testy i ewaluację systemów niedeterministycznych. 🗂️ Requirements: Minimum 3 lata komercyjnego doświadczenia w projektowaniu i wdrażaniu systemów produkcyjnych w Pythonie, Doświadczenie w budowie zaawansowanych architektur LLM (RAG, harness engineering, orkiestracja), Praktyczna znajomość LangChain lub LlamaIndex, Znajomość wzorców projektowych i zasad Clean Code, Doświadczenie w pisaniu testów i ewaluacji systemów niedeterministycznych, Doświadczenie w Data Engineering dla LLM (ETL, parsowanie dokumentów, chunking, transformacje danych), Praca z bibliotekami do manipulacji danymi, Znajomość wektorowych baz danych i strategii chunkingu, Wykształcenie wyższe w kierunku ścisłym lub pokrewnym, Znajomość języka angielskiego na poziomie min. B2 📃 Skills: Python, LLM, RAG, LangChain, LlamaIndex, Pandas, NumPy, Qdrant, Pinecone, Chroma, ETL, Azure, GCP, AWS, Docker, Kubernetes, PyTorch, TensorFlow, C#, Go, Java, SQL, AzureDevOps 🏢 Description: Wymagania: Doświadczenie komercyjne: minimum 3 lata projektowania i wdrażania systemów w jakości produkcyjnej w Pythonie. Udokumentowane doświadczenie w budowaniu zaawansowanych architektur LLM: zaawansowany RAG, harness engineering oraz orkiestracja przy użyciu frameworków takich jak LangChain lub LlamaIndex. Znajomość wzorców projektowych, zasad Clean Code oraz pisania testów i ewaluacji dla systemów niedeterministycznych. Doświadczenie w Data Engineering pod LLM: ETL dla danych nieustrukturyzowanych (parsowanie dokumentów, chunking), transformacji oraz pracy z bibliotekami manipulacji danymi (Pandas, NumPy). Praktyczna znajomość wektorowych baz danych (np. Qdrant, Pinecone, Chroma) oraz strategii chunkingu i zarządzania metadanymi. Umiejętność przekładania skomplikowanych koncepcji AI na język korzyści biznesowych i współpraca z zespołami produktowymi. Wyższe wykształcenie (lub w trakcie) w naukach ścisłych/ilościowych (Informatyka, Matematyka, Fizyka, Ekonometria lub pokrewne) oraz znajomość języka angielskiego na poziomie min. B2. Welcome Skills: Znajomość zaawansowanych frameworków agentowych: LangGraph, CrewAI, AutoGen. Praktyka z chmurami (Azure, GCP lub AWS) oraz konteneryzacją i orkiestracją (Docker, Kubernetes). Zrozumienie klasycznego NLP oraz frameworków głębokiego uczenia (PyTorch, TensorFlow) na potrzeby utrzymania i aktualizacji istniejących komponentów. Znajomość dodatkowego języka (C#, Go, Java). Szczególnie cenimy komercyjne doświadczenie w ekosystemie .NET (C#, SQL Server, Azure PaaS) oraz budowaniu potoków CI/CD (Azure DevOps).

🏢 Summary: Role focused on designing, building, and deploying AI/ML solutions end-to-end, from data exploration and experimentation to production deployment and MLOps. The position combines Data Science, ML Engineering, and collaboration with business stakeholders to translate data into actionable solutions. You will develop and maintain ML pipelines, monitor models, and contribute to AI standards within the organization. 🗂️ Requirements: Minimum 1.5 years of experience in Data Science, ML Engineering or MLOps, Proficiency in Python, Experience with ML/DL libraries (scikit-learn, pandas, numpy, PyTorch or TensorFlow), Knowledge of SQL, Experience working with structured and unstructured data, Experience building and deploying ML/AI models, Knowledge of Docker, Knowledge of Git or GitHub, Understanding of CI/CD basics, Experience with MLflow, DVC or Weights & Biases, Knowledge of statistics, model validation and A/B testing, English level B2 or higher 📃 Skills: Python, SQL, scikit-learn, pandas, numpy, PyTorch, TensorFlow, Docker, Git, GitHub, CI/CD, MLflow, DVC, Weights&Biases, MachineLearning, MLOps, Statistics, ABtesting 🏢 Description: Chcesz tworzyć rozwiązania AI, które mają realny wpływ na biznes? Szukamy osoby, która swobodnie porusza się między analizą danych, Machine Learningiem i MLOps, a jednocześnie potrafi rozmawiać z biznesem i przekładać dane na konkretne decyzje oraz wdrożenia. Dołączysz do zespołu rozwijającego nowoczesne rozwiązania AI — od eksploracji danych i eksperymentów, po wdrożenia modeli i rozwój standardów AI w organizacji. Wymagania Min. 1,5 roku doświadczenia w obszarze Data Science, ML Engineering lub MLOps Bardzo dobra znajomość Python oraz bibliotek ML/DL (scikit-learn, pandas, numpy, PyTorch lub TensorFlow) Znajomość SQL oraz pracy z danymi strukturalnymi i niestrukturalnymi Doświadczenie w budowie i wdrażaniu modeli ML/AI Znajomość Docker, Git/GitHub oraz podstaw CI/CD Doświadczenie z narzędziami MLflow, DVC lub Weights & Biases Wiedza z zakresu statystyki, walidacji modeli i testów A/B Umiejętność współpracy z biznesem i prezentowania wyników analiz Analityczne myślenie, dobra organizacja pracy i nastawienie na rezultat Język angielski min. B2 Mile widziane Wykształcenie kierunkowe (informatyka, matematyka, data science lub pokrewne) Doświadczenie w pracy z politykami bezpieczeństwa danych i etyką AI Zadania na stanowisku Analiza danych i identyfikacja obszarów do wykorzystania AI oraz ML Projektowanie, trenowanie i wdrażanie modeli Machine Learning Prowadzenie eksperymentów i monitorowanie jakości modeli po wdrożeniu Rozwój pipeline’ów CI/CD oraz konteneryzacja środowisk ML z użyciem Docker Wersjonowanie modeli, danych i kodu oraz dokumentowanie prac projektowych Współpraca z zespołami Data Engineering, Backend i DevOps Prezentowanie wyników analiz oraz rekomendacji dla biznesu Udział w rozwoju standardów i rozwiązań AI w organizacji Co oferujemy Udział w nowoczesnych projektach AI i Data Science Pracę z nowoczesnym stackiem technologicznym Realny wpływ na rozwój rozwiązań analitycznych w organizacji Wynagrodzenia złożone z podstawy i premii - regulaminowej rozliczanej kwartalnie (budżet premii 10% wynagrodzenia zasadniczego kwartalnego) Możliwość doskonalenia zawodowego - finansowane przez firmę szkolenia i podnoszenie kwalifikacji Pakiet benefitów - prywatna opieka medyczna, ubezpieczenia grupowe, możliwość skorzystania z pakietu sportowego (karta Multisport) Dostęp do platformy e-learningowej z bogatą bazą kursów Imprezy integracyjne