Jobs / Doctolib
Senior Agents Platform Engineer (x/f/m)
Doctolib · Levallois-Perret, A8, France
Levallois-Perret, A8, FranceFull timeExp: 5+ yrsRemote
Remuneration
Not specified
Location
Levallois-Perret, A8, France
Visa sponsorship
Not specified
Job summary
Build and operate a secure, compliant AI agent platform for healthcare product teams, providing a shared runtime, declarative agent registry, GenAI gateway, and evaluation and observability infrastructure. The role includes managing LLM routing and capacity, reliable streaming and long-running workflows, rollout controls and audit trails, SLOs and incident response, and reference agents. The platform uses Python, LiteLLM, Google ADK, Kubernetes, and managed and self-hosted model providers.
Benefits
Comprehensive health insurance for employee and children25 days of paid vacation per year plus up to 14 days of RTTMental health and coaching servicesLunch vouchers worth €8.50 per working day, with €4.50 employer-coveredSport or creative-class membership subsidy50% reimbursement of public transport subscriptionParentCare birth-leave salary coverageLong-term employee value sharing planCaregiver and disability support packageRelocation support for international mobilityAI tools and dedicated training
Qualifications
- At least five years of software engineering experience
- Hands-on production experience building or operating LLM-based agent systems
- Understanding of agent design patterns and interoperability protocols
- Experience with asynchronous or long-running systems and progressive rollouts
- Experience managing LLM costs and capacity
- Production reliability and security-minded engineering experience
- Excellent communication and collaboration skills
- Fluent English
Responsibilities
- Own the declarative agent manifest and registry
- Operate the LiteLLM-based GenAI gateway, including routing, failover, metering, cost attribution, and reserved-capacity pooling
- Build reliable infrastructure for streaming and long-running agent interactions
- Implement feature-flagged rollouts, emergency kill-switches, and audit trails
- Define SLOs, lead on-call and incident response, and maintain runbooks
- Build online observability and offline evaluation infrastructure
- Ship reference agents and advise feature teams on agent architecture
Skills
AWSAzureDatadogDockerEKSGCPGKEGoHelmJavaKotlinKubernetesKustomizePythonTerraformTypeScriptBigQueryCloud FunctionsCloud RunCloud SQLEnvoyGoogle Cloud StorageGitGitHub ActionsGrafanaGraphQLIstioJiraKafkaKyvernoNGINXOktaOpen Policy AgentOpenAPIOpenTelemetryPostgreSQLPrometheusPub/SubRabbitMQRedisRESTRubyS3SlackVault
Languages
English
Work schedule
Full-time
Travel
Work from abroad for up to 10 days per year
Industry
HealthcareArtificial intelligenceMachine learning
Relocation
Yes