About this role
Responsibilities Design and implement AI-powered applications using LLMs , RAG , and agentic workflow patterns. Build robust backend services, APIs, and necessary integrations for AI-centric solutions. Optimize retrieval pipelines including embeddings , vector search , and hybrid search . Implement comprehensive evaluation, testing, monitoring, and observability for AI applications. Define safe and practical patterns for tool use, human-in-the-loop approval, and agentic behavior. Collaborate with stakeholders to support model selection based on quality, cost, and security. Troubleshoot issues related to retrieval quality, latency, and cost inefficiency in AI systems. Requirements You have 5+ years of experience in backend or full-stack development. You bring 1+ years of experience integrating LLMs or generative AI services into software applications. You possess strong programming skills in Python . You have practical knowledge of RAG , embeddings , vector search , and retrieval quality improvement. You're experienced with MCP , A2A , tool calling, or multi-agent workflows. You have experience designing maintainable services with proper testing , logging , and CI/CD practices. You bring an understanding of AI application evaluation , including quality metrics and regression testing. You have a good understanding of cloud-native application development. You're a proactive communicator with a security-conscious mindset and the ability to explain technical trade-offs. You are fluent in English with active knowledge of French or Dutch . Nice to Haves Familiarity with the Azure cloud environment. Experience with .NET or C# . Experience with AI frameworks such as LangGraph , LangChain , or Semantic Kernel . Experience with Microsoft AI ecosystem tools such as Microsoft Agent Framework or Foundry . Knowledge of vector databases or enterprise search platforms in regulated environments.