Senior AI Engineer - Patient Health Platform (x/f/m)
Doctolib is looking for a Senior AI Engineer to join the Patient Health Platform team in Paris, building the AI-powered Health Companion used by millions of patients. The role designs and builds the production search and recommendation architecture (retrieval, ranking, reranking) with standard and off-the-shelf components, establishing strong baselines and building evaluation and observability into every stage.
Stack
Responsibilities
- ▹Design and build the production search & recommendation architecture: full retrieval, ranking and reranking pipeline with vector search, semantic retrieval and LLM/managed rerankers.
- ▹Establish strong baselines first (prompts, RAG, model selection) before reaching for custom ML.
- ▹Build evaluation and observability into every stage, with offline and online evaluation.
- ▹Set up the 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 closely with PMs and SWEs to define, build and ship AI-powered features.
Requirements
- ▹Significant experience as a Software and/or AI engineer shipping search or recommendation systems to production.
- ▹Ability to ship algorithms to production (ECS-based service on AWS).
- ▹Hands-on experience building end-to-end retrieval, ranking and reranking pipelines; familiar with nDCG, MAP, Recall@k, MRR.
- ▹AI-engineering proficiency: embeddings & vector search, semantic retrieval, RAG, LLM-based or managed rerankers (e.g. Vertex AI), without training a model from scratch.
- ▹Architecture-first approach: build system, baselines, evals and feedback loops with standard tooling, and know when to partner with ML Engineers.
- ▹Evaluation & observability built into every stage: offline and online eval, A/B testing, position-bias handling, monitoring.
- ▹Strong analytical, result-oriented, patient-first mindset.
Nice to have
- ▹Experience at a B2C marketplace (e-commerce, hospitality, travel).
- ▹Additional ML methodologies: pattern mining, recommendation systems, experimentation or causal inference.
- ▹Experience with search engines or information retrieval concepts.
- ▹Exposure to learning-to-rank or feature engineering.
- ▹Experience in a healthcare or other regulated domain (GDPR / HDS).
Soft skills
What we offer
- ▹Free comprehensive health insurance (basic package) for you and your children.
- ▹25 days of paid vacation per year, plus up to 14 days of RTT.
- ▹Free mental health and coaching services via Moka.care.
- ▹Work from abroad up to 10 days per year (flexibility days policy).
- ▹Lunch vouchers (Swile card) worth EUR 8.50/working day, with EUR 4.50 covered by Doctolib.
- ▹Works council subsidy toward sport club or creative class membership.
- ▹50% reimbursement of the public transport subscription.
- ▹Enrollment in the DoctoGrowth long-term employee value sharing plan.
- ▹Parent Care Program: one additional month of leave on top of legal parental leave.
- ▹For caregivers and workers with disabilities: adapted remote policy, extra days off for medical reasons, and psychological support.
About the company
Doctolib builds the AI-powered Health Companion that millions of people rely on daily. Within the Patient domain, the Find Your Practitioner and Preventive & Continuous Care Companion streams shape a product that is a true companion for health, recommended by practitioners and trusted by patients. Permanent, full-time position in Levallois.