Senior AI Engineer — Health Search & Recommendation

Doctolib; Paris (TX); On-site; USD 100,000 - 144,000; Full time

Benefits offered by this job

Health insurance

Paid vacation

Mental health support

Work from abroad (up to 10 days)

Meal vouchers

Transport subsidy

DoctoGrowth plan

ParentCare Program

Job summary

Doctolib seeks a Senior AI Engineer to join the Patient team in Paris. You will design and own the production search and recommendation architecture powering health navigation for millions of patients in Europe.

The role emphasizes end-to-end retrieval, embedding-based vector search, RAG, and LLM-based rerankers, with a strong focus on latency, observability, and scalable ML deployment. Collaboration with ML engineers, PMs, and SWE is essential.

Qualifications

• Significant experience shipping search or recommendation systems to production.
• Hands-on with end-to-end retrieval pipelines (ranking, reranking).
• Experience turning foundation models into production systems (embeddings, vector search, LLM-based rerankers).
• Architectural mindset: build baselines and feedback loops before custom ML.

Responsibilities

• Design and build production search & recommendation architecture (vector search, semantic retrieval, LLM-based rerankers).
• Establish baselines (prompts, RAG, model selection) before custom ML.
• Build evaluation and observability into every stage (offline/online).
• Set up data/event feedback loops to drive iteration.
• Improve search relevance and ranking for patient-facing products.
• Own production quality: latency, reliability, monitoring.
• Partner with ML engineers and collaborate with PMs and SWEs to ship AI-powered features.

Skills

Production deployment

Analytical mindset

AI engineering

Retrieval & ranking

Evaluation & observability

Low-latency systems

Cross-functional collaboration

Tools

AWS ECS

Vertex AI

Job description

Doctolib seeks a Senior AI Engineer to join the Patient team in Paris. You will design and own the production search and recommendation architecture powering health navigation for millions of patients in Europe.

The role emphasizes end-to-end retrieval, embedding-based vector search, RAG, and LLM-based rerankers, with a strong focus on latency, observability, and scalable ML deployment. Collaboration with ML engineers, PMs, and SWE is essential.