Build — AI & agents
Work mode: RemoteAI / Agent Engineer
You build the AI core: agents that take actions, retrieval pipelines that ground them, tool integrations that give them reach, and the evaluation harnesses that keep them honest. This is the engineering at the heart of every engagement.
What you’ll do
- Build agentic workflows and tool integrations against real business systems.
- Design and tune retrieval pipelines that ground model outputs.
- Write evaluation harnesses so quality is measured, not assumed.
- Handle the unglamorous parts: error handling, cost, latency and guardrails.
What we look for
- Strong software engineering, ideally Python or TypeScript.
- Hands-on with LLM APIs, agents and retrieval.
- A rigorous, evaluation-driven approach to AI quality.
- Care for the production concerns, not just the demo.
Nice to have
- Experience with Claude, MCP or agent frameworks.
- Professional French and English.
Apply for this role
Send your CV and a short note on why this role fits. You will hear back from a person, not a tracker.
Other roles in this team
- AI Solutions ArchitectHybridDesigns the end-to-end architecture of the AI solution.
- Forward Deployed EngineerOn-siteEmbeds with the client and builds the solution in their stack.
- Vibe CoderRemoteAI-native builder who ships fast with agentic coding tools.
- Data EngineerRemotePrepares and governs the data AI systems depend on.
Work on AI that ships
Real client systems in production, not demos. If that is the work you want, we should talk.