Senior AI Engineer — Production Search & Recommendation

Doctolib; Paris; On-site; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Free health insurance

Lunch vouchers

RTT days

Work from abroad

Mental health support

Transport subsidy

Job summary

Doctolib is seeking a Senior AI Engineer for the Patient team in Paris to design and deploy production-grade search and recommendation systems. You will work on vector-based retrieval, RAG, and LLM-driven features that guide millions of patients to the right care.

You will partner with ML engineers, PMs, and SWEs to ship AI-powered capabilities with strong emphasis on latency, reliability, and observability across a cloud-native platform.

Qualifications

• Significant experience shipping search or recommendation systems to production.
• Experience turning foundation models into production components (embeddings, vector search, RAG).
• Strong focus on latency, reliability, and maintainability in production.

Responsibilities

• Design and build production search & recommendation architecture with vector search and LLM components.
• Establish baselines (prompts, RAG, model selection) before custom ML.
• Implement evaluation and observability for offline and online testing.
• Create data/event feedback loops to drive ML iteration.
• Collaborate with ML engineers, PMs, and SWE to ship AI-powered features.
• Ensure low-latency, high-quality production services.

Skills

Production deployment

AI engineering

Architecture first

Retrieval & ranking

Observability

Evaluation

End-to-end retrieval

LLM-based/RAG

Tools

AWS ECS

Vector search

Semantic retrieval

Vertex AI

Job description

Doctolib is seeking a Senior AI Engineer for the Patient team in Paris to design and deploy production-grade search and recommendation systems. You will work on vector-based retrieval, RAG, and LLM-driven features that guide millions of patients to the right care.

You will partner with ML engineers, PMs, and SWEs to ship AI-powered capabilities with strong emphasis on latency, reliability, and observability across a cloud-native platform.