Senior AI Solutions Architect with LLM and RAG

🏢 Summary: Opportunity to join a newly formed AI team in the banking sector to build a modern AI-native platform from scratch. The role focuses on designing and delivering production-grade solutions using LLMs, RAG, and agent-based architectures, while shaping AI strategy and architectural decisions. You will develop secure, transparent, and scalable AI systems that drive real business value in a regulated financial environment. 🗂️ Requirements: At least 3 years of experience in AI/ML, Minimum 5 years of experience in product development, Strong Python skills, Hands-on experience with LLMs, RAG, and agent-based systems in production, Experience with AI frameworks such as Agno, LangChain, LlamaIndex or similar, Knowledge of prompt engineering and AI model evaluation, Experience with Azure or AWS, Understanding of vector databases and embeddings, Experience with workflow orchestration tools (Temporal, Prefect, Airflow), Ability to design scalable and reliable AI solutions, Experience in model monitoring and MLOps practices, Ability to make architectural decisions and assess business value of AI, Fluent English 📃 Skills: Python, LLM, RAG, LangChain, LlamaIndex, Agno, Azure, AWS, Temporal, Prefect, Airflow, MLOps, Embeddings, VectorDB 🏢 Description: We are looking for an experienced Senior AI Engineer to join a newly formed AI team delivering a strategic initiative in the banking sector. This is a unique opportunity to co-create a modern AI-native platform from scratch and influence the direction of AI within the organisation. In this role, you will design and develop solutions based on LLMs, RAG systems, and agent-based architectures to support data integration and transformation processes. You will contribute to key decisions around AI strategy, model selection, architecture, and quality standards. We are seeking a candidate with strong technical skills and hands-on experience in building production-grade AI solutions—someone who understands where AI brings real business value and can deliver high-quality, transparent, and secure solutions in a financial environment. Your tasks Design and develop solutions based on LLMs, RAG, and agent-based architectures Co-create and execute an AI strategy for a modern banking platform Select models, frameworks, and approaches for production-grade AI solutions Build systems for data integration, transformation, and validation automation Define prompt engineering, model evaluation, and AI quality standards Develop monitoring, evaluation, and continuous improvement mechanisms Collaborate with engineering and product teams on new features Ensure high quality, transparency, and auditability of AI outputs Contribute to key architectural decisions and AI direction Mentor and share knowledge within the AI team Requirements At least 3 years in AI/ML and a minimum of 5 years in product development Strong Python skills Hands-on experience with LLMs, RAG, and agent-based systems in production Familiarity with frameworks such as Agno, LangChain, LlamaIndex, or similar Knowledge of prompt engineering and AI model evaluation Experience with Azure or AWS Understanding of vector databases and embeddings Experience with workflow orchestration tools (e.g., Temporal, Prefect, Airflow) Ability to design scalable, reliable AI solutions Experience in model monitoring and MLOps practices Capability to make architectural decisions and assess the business value of AI Strong collaboration skills with technical and business stakeholders Fluent English Nice-to-have requirements Previous work in financial services, fintech, or other regulated industries Knowledge of compliance, auditability, and AI security Familiarity with MLOps and large-scale ML/LLM deployments Experience fine-tuning open-source models for specific domains Proven track record in developing AI solutions for data platforms, analytics, or SaaS products Background in AI R&D projects Publications, conference speaking, or open-source contributions Experience building and scaling technical teams What we offer Great Place to Work since 2015 - it’s thanks to feedback from our workers that we get this special title and constantly implement new ideas Employment stability - revenue of PLN 2.1BN, no debts, since 2006 on the market We share the profit with Workers - over PLN 76M has already been allocated for this aim since 2022 Attractive benefits package - private healthcare, benefits cafeteria platform, car discounts and more Comfortable workplace – class A offices or remote work Dozens of fascinating projects for prestigious brands from all over the world PLN 1 000 000 per year for your ideas - with this amount, we support the passions and voluntary actions of our workers Investment in your growth – meetups, webinars, training platform and technology blog – you choose Fantastic atmosphere created by all Sii Power People If you want to work on systems with high operational significance — apply now!

🏢 Summary: Senior-level role focused on designing and delivering scalable AI/ML solutions, including LLMs, RAG, and agent-based systems, from architecture to production deployment. The position involves leading technical decisions, writing high-quality Python code, and building cloud-based microservices solutions. The role also requires translating business needs into robust, production-ready AI systems. 🗂️ Requirements: Several years of software development experience (senior-level), Strong Python proficiency, Solid understanding of ML/AI ecosystem (LLMs, NLP, deep learning), Hands-on experience with RAG, prompt engineering, agent-based systems, Experience with microservices architecture, Experience with databases, Experience with Kubernetes, Experience with CI/CD pipelines, Experience with Azure cloud, English proficiency 📃 Skills: Python, LLMs, RAG, NLP, DeepLearning, PromptEngineering, Microservices, Databases, Kubernetes, CICD, Azure, GCP, Java 🏢 Description: Responsibilities: Design and develop scalable AI/ML solutions (LLMs, RAG, agentic systems) Write high-quality, testable Python code Lead technical architecture and make key design decisions for critical projects Own end-to-end delivery of solutions, from design to production deployment Collaborate with business stakeholders and translate requirements into technical solutions Requirements: Several years of experience as a software developer (senior-level preferred) Very strong Python skills and solid understanding of the ML/AI ecosystem (LLMs, NLP, deep learning) Hands-on experience with RAG, prompt engineering, and agent-based systems Experience with microservices architecture, databases, Kubernetes, and CI/CD pipelines Experience with Azure cloud (GCP as a plus) Basic familiarity with Java is a plus Strong English communication skills

🏢 Summary: The role focuses on engineering production-grade AI features such as semantic search, intelligent assistants, and automated risk scoring by integrating external AI providers into a cybersecurity platform. You will own the full lifecycle from prototype to reliable, monitored production services, primarily using Python on Azure. This position emphasizes robust software engineering practices over model research or training. 🗂️ Requirements: 5+ years of professional experience building production systems in Python, Expert-level Python programming skills, Experience with ML frameworks and libraries, Proven experience shipping and operating production software, Experience integrating external APIs in production environments, Strong understanding of software architecture and design patterns, Practical experience with CI/CD pipelines, Experience with containerization using Docker, Understanding of AI/ML concepts including LLMs, embeddings, prompt engineering, RAG, Experience with unit and integration testing and mocking external services, Polish work permit, Professional proficiency in English 📃 Skills: Python, Azure, OpenAI, Anthropic, Docker, CI/CD, FastAPI, Flask, Pinecone, Weaviate, Chroma, .NET, REST, LLMs, RAG, Embeddings, Git 🏢 Description: About the Role As a Senior AI/ML Engineer you will be building AI-powered features at the core of our platform - semantic search, an intelligent assistant, automated risk scoring, and much more. We mainly integrate with external AI model providers (OpenAI, Anthropic, and others) to deliver these capabilities to our clients and internal users. This is a software engineering role, not a data science or ML research position. You won't train models from scratch or publish papers. You'll engineer production-grade systems that leverage AI to solve real cybersecurity problems. If you're a strong Python engineer excited about making AI reliable, maintainable, and impactful — we want to talk to you. We're looking for a versatile software engineer to own the journey from AI prototype to reliable production system: building robust integrations with external AI providers or fine-tuned models, standardizing our Python codebase and release pipelines, and ensuring our AI features meet the same quality bar as any other production service. What You'll Do Ship AI features end to end - from integration design through deployment to monitoring in production. You'll build and maintain Python services that power our AI-driven capabilities on Azure. Build production-ready AI / ML integrations - including retry logic, rate limiting, cost monitoring, fallback strategies, and abstraction layers that allow us to swap between model providers. Turn proofs of concept into reliable software - collaborate with our AI experts (who bring deep ML/data science expertise) to take working prototypes and engineer them into tested, documented, production-grade services. Standardize Python engineering practices - establish and evolve our code organization, testing strategies, CI/CD pipelines, and release processes for AI/ML features. Design clean service boundaries - our platform's core runs on .NET. You'll design and maintain well-defined APIs between the Python/AI layer and the rest of the system. Mentor and share knowledge - help other engineers grow their Python and AI engineering skills, and bring engineering rigor to the broader team's practices. Contribute to architecture decisions - work closely with other teams to shape how AI capabilities evolve within the platform. Who You Are Must-Haves 🔹 5+ years of professional experience building and maintaining production systems in Python. 🔹 Expert-level programming skills and proficiency with common ML frameworks and libraries. 🔹 A track record of shipping and operating software - not just building prototypes. You care about testing, monitoring, logging, and what happens after deployment. 🔹 Experience integrating external APIs in production systems - ideally AI/LLM provider APIs (OpenAI, Anthropic, Azure AI, or similar), but strong API integration experience in any domain counts. 🔹 Solid understanding of software architecture and design patterns - you have opinions about how to structure a Python project and can articulate trade-offs. 🔹 Practical knowledge of CI/CD pipelines, containerization (Docker), and modern development workflows. 🔹 A working understanding of AI/ML concepts - you know what embeddings, LLMs, prompt engineering, and RAG are. You can have a productive technical conversation with an ML specialist without needing every concept explained from scratch. 🔹 Experience with testing strategies - unit tests, integration tests, mocking external services. You instinctively write tests, not as an afterthought. 🔹 A highly adaptable, problem-solving and result-oriented mindset with the ability to work independently and take ownership in a fast-paced and dynamic environment. 🔹 Strong communication skills in English (our working language). 🔹 Willingness to learn continuously and share what you learn with the team. Nice-to-Haves 🔸 Experience with Azure cloud services. 🔸 Familiarity with FastAPI, Flask, or similar Python web frameworks. 🔸 Exposure to MLOps tooling or practices (model versioning, experiment tracking, feature stores). 🔸 Hands-on experience in Document AI / Intelligent Document Processing using traditional models and Generative AI. 🔸 Experience with vector databases (Pinecone, Weaviate, Chroma, or similar). 🔸 Any experience with .NET - helpful for cross-team collaboration, but not expected. 🔸 Background in or interest in cybersecurity as a domain. Your Team You'll join our Synapse team - a small, focused group responsible for all AI/ML capabilities within our platform. The team consists of: -> Team Leader / Architect - provides high-level architectural guidance, planning, and cross-stack delivery. -> AI / ML Engineer - deep expertise in AI/ML and data science. Your counterbalance: they bring the ML knowledge, you bring the production engineering discipline. -> AI / Backend Engineer - transitioning from .NET into AI engineering. A teammate you'll mentor and grow alongside. -> You - the person who bridges the gap between AI prototypes and reliable production systems. Why Join Us? / What We Offer: Competitive salary and benefits package. Remote work options and flexible working hours. Actual impact on the choice and shape of solutions developed. Opportunities for professional growth and development. Training and conference budget. A collaborative, innovative work environment with an iterative agile approach. The role is for six months with the possibility of extension. Both full-time and part-time cooperation are possible.

🏢 Summary: Senior AI Engineer role focused on building and deploying production-grade AI solutions using Python, FastAPI, Azure, Generative AI, RAG, and agentic frameworks in a hybrid work model. The position includes backend architecture, AI pipeline development, MLOps ownership, and mentoring responsibilities. 🗂️ Requirements: 6–10 years of software engineering experience, Strong AI/ML engineering background, Expertise in Python, Expertise in FastAPI, Experience with LLMs, Experience with RAG pipelines, Experience with vector databases, Hands-on experience with agentic AI frameworks, Production experience with Azure cloud services, Knowledge of MLOps, Experience with Docker, Experience with Kubernetes, Experience with CI/CD 📃 Skills: Python, FastAPI, Azure, LLMs, RAG, Pinecone, Milvus, LangChain, LangGraph, AutoGen, CrewAI, Docker, Kubernetes, CI/CD, MLOps, AKS 🏢 Description: Location: Wroclaw, Poland (Hybrid: 3 days/week in-office) Experience: 6–10 years About the Role We are looking for a Senior AI Engineer to design, develop, and deploy production-grade AI solutions using Python, FastAPI, and Azure, with a strong focus on Generative AI, LLMs, RAG, and agentic frameworks. Key Responsibilities Architect and implement scalable backend services with Python and FastAPI . Build and optimize RAG pipelines using vector databases (e.g., Pinecone, Milvus, Azure Cognitive Search). Develop autonomous agents using agentic AI frameworks (LangChain, LangGraph, AutoGen). Deploy and manage AI workloads on Azure (Azure ML, AKS, OpenAI Service). Own the full ML lifecycle: experimentation, versioning, CI/CD, and monitoring. Mentor junior engineers and drive technical best practices. Required Skills 6–10 years of software engineering experience, with strong focus on AI/ML. Expert in Python and FastAPI . Deep experience with LLMs , RAG , and vector databases . Hands-on experience with agentic frameworks (LangChain, CrewAI, etc.). Production experience with Azure cloud services. Strong understanding of MLOps, containerization (Docker/Kubernetes), and CI/CD.

🏢 Summary: Full-time remote Senior AI Engineer role focused on designing and operating production-grade GenAI systems, including agentic workflows and RAG pipelines integrated into enterprise platforms. The position emphasizes backend engineering, API integrations, and orchestration of LLM capabilities in secure, scalable cloud environments rather than ML research. The role also includes mentoring engineers and establishing best practices for reliable, observable AI services. 🗂️ Requirements: 5+ years professional software development experience, Proficiency in Python, Experience building production LLM applications, Hands-on experience with RAG systems, Experience designing and integrating RESTful APIs, Strong understanding of distributed systems fundamentals, Experience with SQL databases and performance optimization, Experience with vector search, Experience integrating external services via APIs, Knowledge of Azure cloud services, Experience with unit and integration testing, Ability to build AI evaluation and testing frameworks 📃 Skills: Python, REST, GraphQL, SQL, Azure, RAG, LLM, LangChain, LangGraph, ASP.NET, APIs, Microservices, DistributedSystems, Concurrency, AsyncIO, VectorSearch, Embeddings, Caching, AzureFunctions, Storage, KeyVault, AppConfiguration, ApplicationInsights, ServiceBus, EventHubs 🏢 Description: Workload: full-time Work model: 100% Remote We are seeking a Senior AI Engineer who combines strong software engineering fundamentals with hands-on experience building production GenAI solutions, including agentic workflows and Retrieval-Augmented Generation (RAG). This is an engineering and orchestration role focused on integrating LLM capabilities into enterprise systems – not a traditional model-training/ML research role. 5+ years of professional software development experience (ideally 7+ years across backend/API/integration and cloud platforms). Proven ability to ship production-grade LLM applications ( RAG , tool/function calling, agent orchestration) with reliability, security, and observability. Strong ownership mindset and passion for AI engineering – curiosity, experimentation, and a drive to continuously improve the product and the team. Excellent communication and collaboration skills; ability to guide, mentor, and unblock other engineers as we build out an AI engineering capability. Main Responsibilities: Design, build, and operate agentic AI services that orchestrate tools, workflows, and integrations across cloud systems and enterprise data sources. Implement and continuously improve RAG pipelines for tax artifacts and internal knowledge, including ingestion, retrieval tuning, and evaluation. Integrate AI workflows with existing internal platforms (e.g., assistant frameworks) and back-end services through robust APIs. Define and maintain tool/function schemas and orchestration patterns; implement streaming updates, interrupts, and human-in-the-loop steps as needed. Partner with other engineers to set direction, mentor, and unblock the team — helping establish strong foundations for the AI initiative. Build in quality from day one: automated tests, evaluation checks, monitoring/telemetry, and performance optimization for network-bound workloads. Participate in Agile ceremonies (daily scrums, refinement/grooming, planning) and collaborate through peer review, pair programming, and strong documentation. Apply best practices, design principles, and security standards throughout the SDLC, with a focus on reliability and responsible AI. Key Requirements: Strong software engineering background (not a research-only data science profile): designing, building, and operating production systems. Proficiency in at least one backend language used for AI systems (Python preferred). Hands-on experience building and integrating RESTful APIs ; GraphQL experience is a plus. Strong understanding of distributed systems fundamentals : concurrency, async I/O, resiliency/retries, rate limits, caching, and performance optimization. Experience integrating with external services and internal platforms via APIs and event-driven patterns. Solid database fundamentals (SQL design, performance, migrations); experience with vector search is required, and hybrid search stores are a plus. Hands-on experience building LLM-powered applications end-to-end : prompt design, tool/function interfaces, structured outputs, and streaming user experiences. Experience with RAG systems : document ingestion pipelines, chunking/metadata, embeddings, retrieval strategies, grounding, and evaluation. Cloud services expertise : Strong knowledge of Azure cloud services used for enterprise AI solutions (e.g., Functions, Storage, Key Vault, App Configuration, Application Insights). Development practices experience : Strong background in unit and integration testing; ability to build and maintain AI evaluation harnesses (golden sets, regression tests, automated checks). Nice to Have: Direct experience with LangGraph and/or LangChain for multi-agent workflows. Familiarity with emerging agentic ecosystem concepts/protocols (e.g., MCP, A2A, ADK or similar). Experience integrating AI services into .NET (ASP.NET Core) applications or building AI microservices that serve enterprise applications. Experience with event-driven architectures (service bus, event hubs) and real-time updates/streaming to UI. Experience working with tax/enterprise document corpora and governance constraints (PII, retention, access control). Other Details: This position is designed for remote work and has a flexible duration, allowing for innovation in the AI space within an agile environment.

🏢 Summary: Full-time remote Senior AI Engineer role focused on designing and operating production-grade GenAI solutions, including agentic workflows and RAG pipelines integrated into enterprise systems. The position emphasizes software engineering excellence, cloud-based AI services, and orchestration of LLM capabilities rather than model research. You will build reliable, secure, and observable AI services integrated with internal platforms and APIs. 🗂️ Requirements: 5+ years of professional software development experience, Strong background in designing and operating production systems, Proficiency in Python or another backend language for AI systems, Experience building and integrating RESTful APIs, Understanding of distributed systems fundamentals, Experience with API integrations and event-driven architectures, Solid SQL and database design knowledge, Experience with vector search, Hands-on experience building end-to-end LLM applications, Experience implementing RAG pipelines, Strong knowledge of Azure cloud services, Experience with unit and integration testing, Ability to build AI evaluation and regression testing frameworks 📃 Skills: Python, REST, GraphQL, SQL, Azure, RAG, LLM, LangChain, LangGraph, ASP.NET, APIs, Embeddings, VectorSearch, AzureFunctions, AzureStorage, KeyVault, AppConfiguration, ApplicationInsights 🏢 Description: Workload: full-time Work model: 100% Remote We are seeking a Senior AI Engineer who combines strong software engineering fundamentals with hands-on experience building production GenAI solutions, including agentic workflows and Retrieval-Augmented Generation (RAG). This is an engineering and orchestration role focused on integrating LLM capabilities into enterprise systems – not a traditional model-training/ML research role. 5+ years of professional software development experience (ideally 7+ years across backend/API/integration and cloud platforms). Proven ability to ship production-grade LLM applications ( RAG , tool/function calling, agent orchestration) with reliability, security, and observability. Strong ownership mindset and passion for AI engineering – curiosity, experimentation, and a drive to continuously improve the product and the team. Excellent communication and collaboration skills; ability to guide, mentor, and unblock other engineers as we build out an AI engineering capability. Main Responsibilities: Design, build, and operate agentic AI services that orchestrate tools, workflows, and integrations across cloud systems and enterprise data sources. Implement and continuously improve RAG pipelines for tax artifacts and internal knowledge, including ingestion, retrieval tuning, and evaluation. Integrate AI workflows with existing internal platforms (e.g., assistant frameworks) and back-end services through robust APIs. Define and maintain tool/function schemas and orchestration patterns; implement streaming updates, interrupts, and human-in-the-loop steps as needed. Partner with other engineers to set direction, mentor, and unblock the team — helping establish strong foundations for the AI initiative. Build in quality from day one: automated tests, evaluation checks, monitoring/telemetry, and performance optimization for network-bound workloads. Participate in Agile ceremonies (daily scrums, refinement/grooming, planning) and collaborate through peer review, pair programming, and strong documentation. Apply best practices, design principles, and security standards throughout the SDLC, with a focus on reliability and responsible AI. Key Requirements: Strong software engineering background (not a research-only data science profile): designing, building, and operating production systems. Proficiency in at least one backend language used for AI systems (Python preferred). Hands-on experience building and integrating RESTful APIs ; GraphQL experience is a plus. Strong understanding of distributed systems fundamentals : concurrency, async I/O, resiliency/retries, rate limits, caching, and performance optimization. Experience integrating with external services and internal platforms via APIs and event-driven patterns. Solid database fundamentals (SQL design, performance, migrations); experience with vector search is required, and hybrid search stores are a plus. Hands-on experience building LLM-powered applications end-to-end : prompt design, tool/function interfaces, structured outputs, and streaming user experiences. Experience with RAG systems : document ingestion pipelines, chunking/metadata, embeddings, retrieval strategies, grounding, and evaluation. Cloud services expertise : Strong knowledge of Azure cloud services used for enterprise AI solutions (e.g., Functions, Storage, Key Vault, App Configuration, Application Insights). Development practices experience : Strong background in unit and integration testing; ability to build and maintain AI evaluation harnesses (golden sets, regression tests, automated checks). Nice to Have: Direct experience with LangGraph and/or LangChain for multi-agent workflows. Familiarity with emerging agentic ecosystem concepts/protocols (e.g., MCP, A2A, ADK or similar). Experience integrating AI services into .NET (ASP.NET Core) applications or building AI microservices that serve enterprise applications. Experience with event-driven architectures (service bus, event hubs) and real-time updates/streaming to UI. Experience working with tax/enterprise document corpora and governance constraints (PII, retention, access control). Other Details: This position is designed for remote work and has a flexible duration, allowing for innovation in the AI space within an agile environment.

🏢 Summary: The offer is for a backend-focused AI Engineer role building a modern AI platform for business process automation and multi-agent system integration in a production-grade enterprise environment. The position centers on developing scalable Python-based services, secure API integrations, and cloud-native AI solutions using LLMs and RAG. The role involves designing robust, secure, and scalable architectures deployed on AWS or Azure with containerized infrastructure. 🗂️ Requirements: Extensive experience in backend development with Python in production environments, Hands-on experience with AI Agents, RAG, MCP, or LLM-based solutions, Experience with system integrations and API architecture, Experience with scalable cloud-based applications, Experience with AWS or Azure, Experience with Docker and Kubernetes, Experience designing secure and scalable enterprise solutions, Experience with multi-agent systems and workflow automation, Ability to conduct code reviews and mentor developers, Fluent English and Polish 📃 Skills: Python, LLM, RAG, MCP, AWS, Azure, Docker, Kubernetes, API, Microservices, Cloud, AI, Agents 🏢 Description: Additional information The project focuses on building and developing a modern AI platform supporting business process automation and the integration of intelligent agents with enterprise systems. The team is creating scalable solutions based on Python, cloud technologies, and multi-agent architecture, leveraging technologies such as LLMs, RAG, and advanced workflow automation. A key aspect of the project is designing secure integrations between AI platforms, internal systems, and external APIs within a production-grade environment. The project is delivered in an international technology-driven environment with a strong focus on innovation, high-quality architecture, and the development of cutting-edge AI solutions for a global industrial organization. You’re ideal for this role if you: Have extensive experience in backend development with Python in production environments Have hands-on experience with AI technologies such as AI Agents, RAG, MCP, or LLM-based solutions Understand system integrations, API architecture, and scalable cloud-based applications Have worked with AWS or Azure and containerized environments such as Docker and Kubernetes Are experienced in designing secure and scalable enterprise solutions Have strong problem-solving skills and can proactively remove technical blockers Enjoy working closely with cross-functional teams in an international environment Have experience mentoring developers, conducting code reviews, and promoting engineering best practices Are interested in modern AI architectures, workflow automation, and multi-agent systems Communicate fluently in English and Polish and feel comfortable working in a global setup Your day-to-day responsibilities include:​ Designing and developing scalable backend services and AI-driven integration solutions in Python Building and maintaining APIs, connectors, and middleware between AI platforms and enterprise systems Creating and optimizing multi-agent workflows and intelligent automation processes Collaborating with AI Engineers, Data Engineers, and other technical stakeholders on system architecture and integrations Integrating external AI platforms, internal tools, and cloud services into production environments Working with cloud technologies and containerized infrastructure in AWS or Azure environments Improving the quality, reliability, and performance of AI-powered solutions and LLM-based workflows Conducting code reviews, mentoring team members, and supporting engineering best practices Troubleshooting technical issues, identifying bottlenecks, and driving continuous improvements Contributing to technical documentation, architecture discussions, and innovation initiatives across the team