Senior Agents Platform Engineer (x/f/m)
Paris • Full-time
Posted 1mo ago
Job Location
Paris
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
We are seeking a Senior Agents Platform Engineer to join our ML Platform team. Your primary mission will be to develop the foundational platform that enables all feature teams to declare and deploy production-grade, secure, and compliant AI agents. This involves building a shared agent runtime, a unified GenAI gateway, and the necessary observability and evaluation infrastructure to ensure trustworthy AI. You will contribute directly to enhancing the safety, speed, and reliability of AI for patients and healthcare professionals across Europe, working on core features like Consultation Assistant and Phone Assistant.
Responsibilities
- Own the agent manifest and registry, designing a declarative specification for skills, tools, memory, model, guardrails, and security to automatically integrate agents into the platform.
- Manage the GenAI gateway end-to-end, including routing, failover, metering, cost attribution, capacity pooling, and guardrails across self-hosted and managed providers, handling hundreds of millions of requests monthly.
- Build and operate infrastructure for long-running, streaming agent interactions, ensuring production-grade reliability for SSE/WebSocket connections, queueing, retries, human-in-the-loop approvals, and sandboxed execution.
- Develop feature-flagged, progressive rollout mechanisms for prompts, models, and configurations, including an emergency kill-switch and audit trails for secure handling of sensitive healthcare data.
- Take ownership of the agents platform's end-to-end reliability, defining SLOs, leading on-call and incident response, and developing runbooks for provider failover.
- Construct the observability and evaluation layer, encompassing online traces, logs, offline evaluations (LLM-as-judge, simulators), and a compliance-grade audit trail for health data.
- Validate the platform by shipping reference agents and advising feature teams on agent architecture trade-offs.
Requirements
- 5+ years of software engineering experience, with hands-on production experience building or operating LLM-based agent systems.
- Solid understanding of agent design patterns including 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).
- Experience with control-plane concepts for asynchronous or long-running systems (queueing, retries, checkpointing).
- Experience with feature-flagging or progressive-rollout systems including reliable kill-switches.
- Experience managing cost and capacity for LLM usage, including routing, caching, and reserved-capacity planning.
- Comfortable owning production reliability (SLOs, incident response, on-call) and security-minded design for sandboxing, permission scoping, and audit trails.
- Excellent communication and collaboration skills, high agency, and a pragmatic build-vs-buy mindset.
- Fluent in English.
