Développeur IA Générative Confirmé (H/F)
Core
Designing end-to-end RAG pipelines, integrating LLMs into robust architectures, and developing conversational AI agents for enterprise clients.
Role type
Senior Generative AI Engineer (RAG & LLMs)
Builds
Production-ready RAG pipelines, conversational assistants, and multi-step AI agents for large enterprise clients.
Domain
Enterprise AI, Generative AI, RAG, NLP
Deliverable
production ML models
Required skills
Python (FastAPI, Pydantic, asyncio), RAG architecture design, Vector databases (Azure AI Search, Elasticsearch, Qdrant, Pinecone), LLM frameworks (LangChain, LangGraph, LlamaIndex, Semantic Kernel), Containerization (Docker, Kubernetes), CI/CD, Observability (Grafana, Langfuse), API development, Microservices
Preferred skills
OCR and document processing, LLMOps, Cloud platforms (AWS, Azure, GCP), GDPR and AI Act compliance, Banking/Insurance/Public sector experience
Technologies
Mistral, Azure OpenAI, OpenAI, Claude, Bedrock, FastAPI, Pydantic, asyncio, LangChain, LangGraph, LlamaIndex, Semantic Kernel, Docker, Kubernetes, Terraform, GitLab CI, Grafana, Langfuse, Azure AI Search, Elasticsearch, Qdrant, Pinecone
Responsibilities
Design end-to-end RAG pipelines (ingestion, chunking, embeddings, indexing), Integrate LLMs into robust architectures, Develop conversational assistants and multi-step AI agents, Handle document use cases (OCR, information extraction, search, synthesis), Expose AI capabilities via APIs and microservices, Industrialize solutions with testing and CI/CD, Monitor model quality (prompts, latency, costs, hallucinations, guardrails), Advise clients on feasibility and realistic implementation
Seniority
Senior, hands-on IC
