1 day ago
Luxembourg, LuxembourgSenior
Responsibilities
- Develop backend services and REST APIs with Python and FastAPI, including asynchronous processing, input validation, authentication, error handling, and business-system integrations.
- Implement stateful agentic workflows with LangGraph and LangChain, including routing, tools, memory, persistence, retries, failure handling, and human-in-the-loop interactions.
- Integrate LLMs through Azure OpenAI, OpenAI, Mistral, or IBM watsonx while managing structured outputs, rate limits, latency, costs, and service failures.
- Design RAG ingestion and retrieval pipelines covering extraction, chunking, embeddings, vector databases, hybrid search, reranking, source citations, and quality evaluation.
- Build automated unit, integration, and asynchronous tests and use LangSmith or equivalent tools to trace workflows and analyze failures.
- Containerize applications with Docker, contribute to CI/CD pipelines, and support cloud deployments, preferably on Microsoft Azure.
- Use AI-assisted development tools for rapid prototyping while reviewing, testing, securing, and maintaining generated code.
- Apply responsible AI practices covering privacy, transparency, traceability, human oversight, authentication, access control, and secrets management.
- Document technical decisions and contribute to solution estimates, feasibility studies, demonstrations, and collaboration with engineering, architecture, security, compliance, and business teams.
Requirements
- Strong practical Python and asynchronous programming experience, including asyncio, concurrent API calls, timeouts, retries, cancellation, and task management.
- Advanced experience with FastAPI and REST API design, input validation, authentication, and consistent error management.
- Strong LangGraph and LangChain experience, including state management, routing, persistence, memory, tool integration, prompting, structured outputs, and human-in-the-loop workflows.
- Practical experience integrating Azure OpenAI, OpenAI, or equivalent LLM providers and managing rate limits, latency, costs, and failures.
- Experience designing RAG systems with data ingestion, chunking, embeddings, vector databases, hybrid search, reranking, citations, and retrieval-quality evaluation.
- Experience implementing multi-agent coordination, delegation, context sharing, failure handling, MCP clients or servers, and A2A integrations.
- Experience with LangSmith or equivalent observability and evaluation tools for LLM applications and agentic workflows.
- Experience with AI-assisted development tools such as Claude Code, GitHub Copilot, or Codex, including prompt formulation, code review, and test validation.
- Proficiency with Git, Docker, pytest, and software testing practices, plus experience deploying applications to a cloud platform, ideally Microsoft Azure.
- Knowledge of EU AI Act and GDPR implications for data protection, human oversight, transparency, traceability, and responsible AI development.
- Professional fluency in both French and English, written and spoken.
- Relevant Microsoft AI, Claude, cloud engineering, AI engineering, AI governance, or multi-agent architecture certifications are advantageous.
About Fujitsu
Fujitsu is a Japanese multinational IT services and computing company that provides systems integration, managed services, cloud, and enterprise hardware for businesses and governments. It also develops servers, storage, and client devices for enterprise workloads. Founded in 1935 and headquartered in Tokyo, Fujitsu is publicly listed on the Tokyo Stock Exchange and operates in more than 50 countries.