AI Developer (Python / RAG / GenAI)

Quick Facts

AI Developer focused on Generative AI and LLM solutions using a Retrieval-Augmented Generation (RAG) architecture.

Description

Design, build, and scale production AI solutions based on Generative AI and Large Language Models (LLMs). Work on RAG systems that connect LLMs to enterprise knowledge sources, including document ingestion and retrieval pipelines. Implement scalable Python backend services and evaluate/monitor answer quality, compliance with sources, latency, and costs.

Responsibilities

• Design and develop RAG-based AI solutions using LLMs and corporate knowledge sources.
• Build document-processing pipelines: ingestion, parsing, chunking, embedding, indexing, retrieval, re-ranking, and response generation.
• Integrate LLMs with vector databases, search services, APIs, and enterprise systems.
• Optimize prompts, search strategies, and context management to improve answer quality and reduce hallucinations.
• Implement evaluation and monitoring for search quality, answer accuracy, source compliance, response time, and costs.
• Develop scalable backend services and APIs in Python.
• Implement security mechanisms, authorization, citation, and traceability of information sources.
• Collaborate with architecture, engineering, DevOps/MLOps, and business teams during testing, deployment, and continuous improvement.

Requirements

• Very strong Python skills with experience building production backend applications and AI services.
• Hands-on experience with Generative AI and LLMs (prompt engineering, context management, structured outputs).
• Experience designing and implementing RAG solutions.
• Knowledge of the full RAG process: document processing, chunking, embeddings, indexing, retrieval, re-ranking, and response generation.
• Experience with at least one LLM platform/API such as Azure OpenAI, OpenAI API, AWS Bedrock, or Google Vertex AI.
• Experience with AI orchestration frameworks like LangChain, LlamaIndex, Semantic Kernel, or similar.
• Knowledge of vector databases and semantic search tools such as Azure AI Search, PostgreSQL/pgvector, Pinecone, Weaviate, Qdrant, Elasticsearch, or OpenSearch.
• Knowledge of Git, automated testing, and modern software development practices.
• Practical Docker and containerization experience.
• Experience with CI/CD pipelines and deploying applications to cloud environments.
• English proficiency at B2/C1 level.

Benefits

Not specified in the provided posting.