AI Engineer — Agents LLM in Production (Python / LangGraph)

Project overview

Ever"T — AI-native, innovative, and hyper-growth tech consulting firm — is looking for an AI Engineer to strengthen an already structured AI team, within a high-volume French tech player.

The Context

You will join a team of 12 AI Engineers, with a clear model: each engineer is embedded directly into a business team, in contact with the business. No isolated labs, no sleeping POCs — what is built goes into production and serves real users.

The team is young, the foundations are laid, but the entire playground remains to be written: agent patterns, evaluation, industrialization, team standards. This is a rare moment to influence how things are done.

The Project

Design and deploy an LLM agent for a business team (creative/marketing or customer relations universe depending on the scope chosen): framing the need with stakeholders, designing the orchestration, deployment, evaluation, and continuous iteration.

Responsibilities

• Design multi-step LLM agents (orchestration, tools, state management) with LangGraph
• Build and stabilize RAG chains: retrieval, response quality, evaluation
• Continuously arbitrate quality / cost / latency / complexity trade-offs
• Industrialize: observability, evaluation sets, non-regression, production monitoring
• Exchange directly with business teams: frame a vague need, simplify, challenge, measure delivered value

Project details

• Start: flexible
• Remote: hybrid
• Location: Paris, France, FR
• Languages: French