AI Engineer

HilbertAmsterdamHybridFull-time4 days ago

Hilbert is hiring an AI Engineer in Amsterdam to build production-grade agentic AI systems end-to-end, starting with the evaluation and testing layer for their agents. The role requires 4+ years of production software engineering, including 2+ years building LLM or agent systems shipped to real users, with hands-on LangChain/LangGraph experience.

What you'll do

Own the evaluation layer for agents: harnesses, metrics, golden datasets, regression gates, and human-in-the-loop review
Architect and implement agent workflows using LangChain, LangGraph, or equivalent, including state memory, routing, tool registries, and recovery paths
Own systems from experimentation through production and operate them once live: tracing, monitoring, latency, cost-per-task budgeting, and on-call
Diagnose real production failures and turn each into a durable fix and a test
Set the technical standard for agent work at Hilbert: review designs, define patterns, and raise the bar across the team
Collaborate closely with the founding team and cross-functional partners, communicating tradeoffs, progress, and technical decisions
Make pragmatic engineering decisions under ambiguity: ship, learn, iterate

What you need

Must-have

LangChainLangGraphLLMAgent systemsRAGGraph-based retrievalAPIsData infrastructure

Nice-to-have

LangfuseConstrained decodingHybrid retrievalChunking and embedding strategyRankingGroundingCost/latency optimization

Soft skills

Clear communicationOwnershipComfort with ambiguityStartup speedCollaborationPragmatic decision-making

AI EngineerAgentic AILLMRAGLangChainLangGraphEvaluationStartupTechnologyHybrid

/What you'll do

/What you need

Must-have

Nice-to-have

Soft skills

What you'll do

What you need