12 hours ago
Paris, FranceSenior
Responsibilities
- Own the declarative agent manifest and registry covering skills, tools, memory, models, guardrails, sandboxing, and security.
- Own the LiteLLM GenAI gateway, including routing, failover, metering, cost attribution, capacity pooling, and guardrails across self-hosted and managed providers.
- Build reliable infrastructure for long-running and streaming agent interactions, including SSE/WebSocket connections, queueing, retries, approvals, and snapshot/resume.
- Implement feature-flagged progressive rollouts, emergency kill-switches, and audit trails for prompts, models, configurations, and sensitive healthcare data.
- Own platform reliability through SLOs, on-call, incident response, runbooks, and provider failover.
- Build observability and evaluation infrastructure using traces, logs, offline evaluations, simulators, CI gating, and compliance-grade audit trails.
- Validate the platform by shipping reference agents and advise feature teams on agent architecture trade-offs.
Requirements
- 5+ years of software engineering experience, including hands-on production experience building or operating LLM-based agent systems such as Google ADK or similar.
- Understanding of agent design patterns including planning and reflection loops, tool calling, state and memory management, multi-agent coordination, and human-in-the-loop checkpoints.
- Experience with MCP, A2A, AG-UI, asynchronous control planes, queueing, retries, checkpointing, feature flags, and progressive rollouts.
- Experience managing LLM usage costs and capacity through routing, caching, and reserved-capacity planning with managed model providers.
- Production reliability experience covering SLOs, incident response, on-call, sandboxing, permission scoping, and audit trails for autonomous systems.
- Preferred experience with long-term memory, artifact stores, RAG pipelines, production-trace evaluation datasets, Kubernetes CRDs/operators, Temporal, and regulated environments.
- Fluent English and strong communication, collaboration, pragmatic build-versus-buy judgment, and comfort shaping scope in a founding role.
Benefits
- Free comprehensive basic health insurance for the employee and children.
- 25 days of paid vacation plus up to 14 days of RTT.
- Free mental health and coaching services through Moka.care.
- Work from abroad for up to 10 days per year.
- Lunch vouchers worth €8.50 per working day, with €4.50 covered by Doctolib.
- Work council subsidy for sport club or creative class membership.
- 50% reimbursement of public transport subscriptions.
- ParentCare salary coverage during birth leave.
- Long-term employee value-sharing plan through DoctoGrowth.
- Additional support for caregivers and workers with disabilities, including remote-policy adaptations, medical leave, and psychological support.
- Relocation support for international mobility and access to AI coding tools and dedicated training.
- Permanent, full-time position in Paris, France, with a hybrid setup of up to two remote days per week; start as soon as possible.
Tech Stack
AWSAzureDatadogDockerGoGoogle Cloud PlatformHelmJavaKotlinKubernetesMLflowPythonReact NativeRuby on RailsSwiftTerraformTypeScript
Categories
About Doctolib
Doctolib builds a digital healthcare platform for patients and medical professionals, combining online appointment booking, teleconsultations, and practice-management software. It monetizes via SaaS subscriptions to healthcare providers, while access for patients is free. Founded in 2013 and headquartered in Levallois‑Perret, the privately held company operates across France, Germany, Italy, and the Netherlands and is certified as a B Corp.