Senior AI Engineer - Patient Search & Recs (Paris)

Doctolib; Paris; Sur place; EUR 110 000 - 150 000; Plein temps

Avantages offerts par ce poste

Health insurance

Vacation days

Mental health services

Work from abroad

Lunch vouchers

Sport club subsidy

Transport subsidy

DoctoGrowth

ParentCare program

Disability accommodation

Résumé du poste

Doctolib is seeking a Senior AI Engineer for the Patient team in Paris to design and own search and recommendation systems powering patient access to care. You will work with ML Engineers, PMs, and SWEs to deliver fast, trusted AI-powered features at scale across Europe.

The role focuses on end-to-end retrieval pipelines, vector search, embedding models, and production-ready pipelines with strong emphasis on observability, latency, and reliability.

Qualifications

• Production deployment to production (ECS-based service on AWS).
• Strong analytical mindset: result-oriented, patient-first approach.
• Significant experience as a software or AI engineer shipping search or recommendation systems to production.
• Hands-on experience building end-to-end retrieval: ranking, reranking pipelines and familiarity with nDCG, MAP, Recall@k, MRR.
• AI-engineering proficiency: embeddings & vector search, semantic retrieval, RAG, LLM-based or managed rerankers.
• Architecture-first approach: build the system, baselines, evals, and feedback loops with standard tooling.
• Evaluation & observability built into every stage (retrieval, ranker, reranker) – offline/online eval, A/B testing, position-bias handling, monitoring.
• Production deployment – low-latency services with high SLA targets.

Responsabilités

• Design and build the production search & recommendation architecture: full retrieval, ranking, reranking pipeline with standard and off-the-shelf components.
• Build evaluation and observability into every stage, with offline and online evaluation.
• Set up data/event feedback loops that drive iteration and feed deeper ML later.
• Improve search relevance and ranking on patient-facing products, raising result quality.
• Own production quality: latency reliability, monitoring, and maintainability.
• Partner with ML Engineers and collaborate with PMs and SWEs to define, build, and ship AI-powered features.

Connaissances

Production deployment

Analytical mindset

AI software engineering

Retrieval & ranking

LLM-based rerankers

Vector search

System architecture

Observability

Outils

AWS ECS

Vertex AI

Description du poste

Doctolib is seeking a Senior AI Engineer for the Patient team in Paris to design and own search and recommendation systems powering patient access to care. You will work with ML Engineers, PMs, and SWEs to deliver fast, trusted AI-powered features at scale across Europe.

The role focuses on end-to-end retrieval pipelines, vector search, embedding models, and production-ready pipelines with strong emphasis on observability, latency, and reliability.