SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Doctolib is seeking a Senior Agents Platform Engineer to join the ML Platform (TIGER) team in AI & Machine Learning. Your mission is to build the foundational platform that enables every feature team at Doctolib to declare an agent once and receive a production-grade, secure, and compliant AI agent by default. You will work on the shared agent runtime, unified GenAI gateway, and observability/evaluation infrastructure powering Consultation Assistant, Phone Assistant, Health Companion, and more—contributing to safer, faster, and more reliable AI for patients and care teams across Europe.
Key Responsibilities:
- Own the agent manifest and registry: design the single declarative specification (skills, tools, memory, model, guardrails, sandbox, security) that automatically wires new agents into the full platform, triggerable from product surfaces, other agents (A2A), schedules, or workflows.
- Own the GenAI gateway end-to-end (built on LiteLLM): manage routing (including KV-cache-aware routing), failover, metering, cost attribution, reserved-capacity pooling, and guardrails across self-hosted (vLLM) and managed providers, serving several hundred million requests per month.
- Operate infrastructure for long-running, streaming agent interactions: build production-grade reliability for SSE/WebSocket connections, queueing and retries, human-in-the-loop approvals, and snapshot/resume in a sandboxed execution environment.
- Build feature-flagged, progressive rollout for prompts, models, and configs with emergency kill-switches and audit trails for sensitive healthcare data.
- Own end-to-end reliability for the agents platform: define SLOs, lead on-call and incident response, build runbooks including provider failover for the GenAI gateway.
- Build observability and evaluation layer: online traces and logs, offline evals (LLM-as-judge plus patient and practitioner simulators) gating CI, and compliance-grade audit trails for health data.
- Validate the platform by shipping one or two reference agents yourself before product teams adopt it; advise feature teams on agent architecture trade-offs.
Tech Stack: Python, LiteLLM, Google Agent Development Kit (ADK), Kubernetes (GKE/EKS), MCP/A2A/AG-UI protocols, Flagd, MLflow, Braintrust, Datadog, Terraform, Docker, Helm.
Requirements:
- 5+ years of software engineering experience, including hands-on production experience building or operating LLM-based agent systems (Google ADK or similar).
- 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), and feature-flagging or progressive-rollout systems including reliable kill-switches.
- Experience managing cost and capacity for LLM usage—routing, caching, and reserved-capacity planning with managed model providers.
- Comfortable owning production reliability (SLOs, incident response, on-call) and security-minded when designing sandboxing, permission scoping, and audit trails for autonomous systems acting on sensitive data.
- Excellent communication and collaboration skills, high agency, pragmatic build-vs-buy mindset, comfortable working in a founding role where shaping scope is part of the job.
- Fluent in English.
Nice-to-Have:
- Experience giving agents richer identity, memory, and knowledge (long-term memory, artifact stores, RAG pipelines) or building feedback loops that turn production traces into evaluation datasets.
- Experience building Kubernetes-native abstractions (CRDs/operators) or durable stateful execution engines (e.g., Temporal) for long-running workflows.
- Experience in regulated environments (healthcare, finance, public sector) and frameworks such as GDPR, HDS, ISO 27001, or SOC 2.
