Software Engineer – Python & LLM Integration

Responsibilities

• Design and implement AI-powered applications using LLMs, RAG, and agentic workflow patterns.
• Build backend services, APIs, and integrations required for AI-centric applications.
• Optimize retrieval pipelines including chunking, embeddings, vector search, and hybrid search.
• Implement evaluation, testing, monitoring, and observability frameworks for AI-driven solutions.
• Collaborate with stakeholders to define safe patterns for tool use and human-in-the-loop workflows.
• Troubleshoot complex issues including hallucinations, poor retrieval quality, and high latency.

Requirements

• You bring 5+ years of software engineering experience, preferably in backend or full-stack development.
• You possess 1+ years of experience integrating LLMs or other generative AI services into software applications.
• You have practical knowledge of RAG, embeddings, vector search, and retrieval quality improvement.
• You have strong programming skills in Python.
• You possess experience with MCP, A2A, tool calling, or multi-agent workflows.
• You have experience designing maintainable services with CI/CD, logging, and deployment practices.
• You bring a solid understanding of cloud-native application development and security-conscious design.
• You're able to evaluate AI application quality using test datasets and regression testing metrics.
• You are fluent in English with active knowledge of French or Dutch.

Nice to Haves

• Experience with AI frameworks such as LangGraph, LangChain, or Semantic Kernel.
• Familiarity with the Azure cloud environment and its AI ecosystem tools.
• Experience with backend development in .NET or C#.
• Knowledge of vector databases or enterprise search platforms.
• Experience working in regulated or security-sensitive enterprise environments.