Senior Agents Engineer: GenAI Gateway & Observability

Doctolib; Paris; Hybrid; EUR 120,000 - 160,000; Full time

Benefits offered by this job

Free comprehensive health insurance (+

25 days vacation + RTT

Lunch vouchers

Job summary

Doctolib is seeking a Senior Agents Platform Engineer to build and operate the AI agent platform powering our healthcare products. You’ll own the declarative agent specification, gateway routing, and an observable, secure runtime for agent interactions.

You will lead reliability, cost management, and governance across self-hosted and managed AI providers, contributing to compliant, production-grade AI for patients and care teams across Europe.

Qualifications

• 5+ years of software engineering experience, including hands-on production experience building or operating LLM-based agent systems.
• Solid understanding of agent design patterns: planning/reflection loops, tool calling, state and memory management, multi-agent coordination, and human-in-the-loop checkpoints.
• Experience with agent interoperability and tool protocols (MCP, A2A, AG-UI), control-plane concepts for asynchronous or long-running systems (queueing, retries, checkpointing).
• Experience managing cost and capacity for LLM usage — routing, caching, and reserved-capacity planning with managed model providers.
• Security-minded when designing sandboxing, permission scoping, and audit trails for autonomous systems acting on sensitive data.
• Fluent in English.

Responsibilities

• Own the agent manifest and registry — design the single declarative specification wiring any new agent into the full platform automatically.
• Own the GenAI gateway end to end (built on LiteLLM) — manage routing, failover, metering, cost attribution, and guardrails across self-hosted and managed providers.
• Operate the infrastructure for long-running, streaming agent interactions — build reliability for SSE/WebSocket connections, queueing and retries, and sandboxed execution.
• Build feature-flagged, progressive rollout for prompts, models, and configs — including an emergency kill-switch and audit trail for health data.

Skills

LLM agent systems

Agent design patterns

Production reliability

English fluency

Tools

Google ADK

LiteLLM

Kubernetes

Terraform

Datadog

MLflow

Job description

Doctolib is seeking a Senior Agents Platform Engineer to build and operate the AI agent platform powering our healthcare products. You’ll own the declarative agent specification, gateway routing, and an observable, secure runtime for agent interactions.

You will lead reliability, cost management, and governance across self-hosted and managed AI providers, contributing to compliant, production-grade AI for patients and care teams across Europe.