Senior AI Engineer, Health Search & Recommendation

Doctolib; Paris; On-site; EUR 110,000 - 170,000; Full time

Benefits offered by this job

Health insurance

25 days vacation + RTT

Lunch vouchers

Mental health & coaching services

Work from abroad up to 10 days/year

Job summary

Doctolib is seeking a Senior AI Engineer to join the Patient team in Paris. You will design and own production search and recommendation engines powering health navigation for millions across Europe, focusing on fast, trustworthy results and scalable architecture.

You will ship end-to-end retrieval pipelines, evaluate with offline/online tests, and collaborate with ML engineers, PMs, and SWEs to deliver impactful AI-powered features while maintaining low latency and reliability.

Qualifications

• Experience shipping production search or recommendation systems.
• Experience deploying algorithms to production (ECS-based service on AWS).
• Hands-on ability to build end-to-end retrieval pipelines (ranking, reranking).
• Familiarity with embeddings, vector search and LLM-based or managed rerankers.

Responsibilities

• Design and build production search & recommendation architecture (retrieval, ranking, reranking).
• Establish strong baselines (prompts, RAG, model selection) before custom ML.
• Build evaluation and observability into all stages with offline/online testing.
• Set up data/event feedback loops for iterative improvement.
• Improve search relevance and ranking on patient-facing products.

Skills

Production deployment

Analytical mindset

AI engineering

End-to-end retrieval

Architecture-first

Observability

Low-latency deployment

Collaboration with ML engineers

Tools

ECS on AWS

Vector search

Job description

Doctolib is seeking a Senior AI Engineer to join the Patient team in Paris. You will design and own production search and recommendation engines powering health navigation for millions across Europe, focusing on fast, trustworthy results and scalable architecture.

You will ship end-to-end retrieval pipelines, evaluate with offline/online tests, and collaborate with ML engineers, PMs, and SWEs to deliver impactful AI-powered features while maintaining low latency and reliability.