GenAI Engineer

Your team

Your role

• Designing, testing, and refining high-quality prompts and chains of thought to solve real-world business problems using LLMs.
• Building robust and scalable LLM-based pipelines using tools like LangChain and LangGraph.
• Integrating external APIs, vector databases, retrieval systems, and agent logic into production-grade AI workflows.
• Continuously evaluating and comparing different LLMs (open-source and proprietary) to select the most suitable models for specific use cases.
• Instrumenting, monitoring, and debugging multi-step AI workflows using tools such as Langfuse and CloudWatch.
• Working closely with product and engineering teams to translate functional goals into effective LLM-driven solutions.
• Staying hands-on with the latest advancements in AI orchestration, reasoning frameworks, and tooling.

Your profile

• Proven experience in building and deploying applications using Generative AI, LLMs, and agent frameworks.
• Deep hands-on knowledge of LangChain, LangGraph, and vector databases (e.g. Qdrant, Pinecone, FAISS).
• Strong Python development skills, including experience with CI/CD and containerized environments (Docker, GitHub Actions).
• Familiarity with LLM evaluation methods, prompt optimization, and multi-agent workflows.
• Experience using cloud services, ideally AWS (e.g., Bedrock, SageMaker, Lambda, S3).
• Analytical mindset with the ability to break down complex problems and test multiple solutions iteratively.
• Curious, self-driven, and able to work independently on end-to-end delivery.
• Must be resident in Switzerland or willing to relocate.

Note

Diversity & Inclusion