Staff Machine Learning Engineer - Retrieval (x/f/m)

About this role

<h2><strong>Set a new pulse for healthcare!</strong></h2> <p>We are looking for a <strong>Staff Machine Learning Engineer - Retrieval</strong> to join our AI team working on Clinical decision support and Medical Knowledge.</p> <p>Your mission will be to ground clinical AI decisions in validated, trusted medical sources from HAS guidelines and learned society recommendations to peer-reviewed clinical studies. You will work in a feature team developing Doctolib's <strong>Medical Knowledge Platform</strong>, contributing directly to the reliability and safety of AI-powered healthcare experiences used by hundreds of thousands of health professionals and millions of patients across Europe.</p> <p>Working in the tech team at Doctolib means building innovative products and features to improve the daily lives of care teams and patients.</p> <h2>&nbsp;</h2> <h2><strong>What you'll do</strong></h2> <p>Your responsibilities include but are not limited to:</p> <ul> <li>Build and own Doctolib's Medical Knowledge Platform, designing the systems that ground clinical AI decisions in validated medical sources (HAS guidelines, learned society recommendations, clinical studies)</li> <li>Design and maintain both indexing pipelines and retrieval systems, ensuring end-to-end ownership across the full retrieval stack</li> <li>Operate at scale: architect and optimize systems handling 100M+ documents, 50+ req/s, and sub-300ms latency requirements</li> <li>Build custom re-rankers, optimize query processing pipelines, and design robust retrieval evaluation frameworks</li> <li>Engineer deep RAG systems from the ground up - going well beyond off-the-shelf components to tackle real medical knowledge complexity</li> <li>Work across the full retrieval stack: vector embeddings, vector search, re-ranking, query expansion and rewriting</li> </ul> <h2>&nbsp;</h2> <h2><strong>Who you are</strong></h2> <p>Before you read on: if you don't have the exact profile described below, but you feel this job description matches your skill set, we still encourage you to apply.</p> <p><strong>You'll be a great fit if you:</strong></p> <ul> <li>Have proven production experience building and scaling search &amp; retrieval systems in a real-world, high-traffic environment&nbsp;</li> <li>Bring deep dual expertise in both offline indexing and online retrieval; you own the full pipeline, not just one side of it.</li> <li>Are genuinely hands-on with the retrieval tech stack: Elasticsearch, Solr, Vertex AI, vector search, embeddings, re-ranking and query processing.</li> <li>Have gone beyond commodity RAG; you've built custom re-rankers, optimized indexing pipelines, or engineered query processing solutions that required real technical depth.</li> <li>Have operated at Senior or Staff level, with the autonomy and technical depth that comes with it.</li> </ul> <p>&nbsp;</p> <p><strong>It would be fantastic if you:</strong></p> <ul> <li>Have experience working with medical knowledge sources, clinical databases, or healthcare information systems</li> <li>Have contributed to evaluation frameworks and benchmarks for retrieval quality or AI outputs in regulated or high-stakes environments</li> <li>Have worked in a multi-lingual retrieval context or with domain-specific ontologies</li> </ul> <h2>&nbsp;</h2> <h2><strong>Life at Doctolib Tech</strong></h2> <ul> <li>Our solutions are built on a single fully cloud-native platform that supports web and mobile app interfaces, multiple languages, and is adapted to country and healthcare specialty requirements.</li> <li>Our stack is composed of Rails, TypeScript, Java, Python, Kotlin, Swift, and React Native.</li> <li>We leverage AI ethically across our products to empower patients and health professionals. Discover our AI vision <a href="https://careers.doctolib.com/ai-careers/">here</a>.</li> </ul> <p><em>Want to learn more about our tech culture and environment? Visit the</em><a href="https://careers.doctolib.com/tech-doctolib/"><em> </em><em>Doctolib Tech site</em></a><em>.</em></p> <h2>&nbsp;</h2> <h2><strong>What we offer</strong></h2> <ul> <li>Free comprehensive health insurance (basic package) for you and your children</li> <li>25 days of paid vacation per year, plus up to 14 days of RTT</li> <li>Free mental health and coaching services through our partner Moka.care</li> <li>Work from abroad for up to 10 days per year thanks to our flexibility days policy</li> <li>Lunch vouchers (Swile card) worth €8.50 per working day, with €4.50 covered by Doctolib</li> <li>A subsidy from the work council to refund part of the membership to a sport club or a creative class</li> <li>50% reimbursement of your public transport subscription</li> <li>ParentCare Program: Enjoy full salary coverage (100%) during your first month of birth leave and 75% during the second, covered by Doctolib</li> <li>Enrollment in Doctolib's long-term employee value sharing plan called DoctoGrowth</li> <li>For caregivers and workers with disabilities, a package including an adaptation of the remote policy, extra days off for medical reasons, and psychological support</li> <li>Relocation support in case of international mobility</li> <li>Access to the best AI tools for coding, development and dedicated training</li> </ul> <h2>&nbsp;</h2> <h2><strong>Our interview process</strong></h2> <ul> <li>Recruiter Screen (45')</li> <li>Live Coding Interview (75')</li> <li>System Design Interview (75')</li> <li>Behavioural Interview (75')</li> <li>Reference Check &amp; Offer</li> </ul> <p>We want your experience to be clear, respectful, and transparent. Learn more about our hiring process on our<a href="https://careers.doctolib.com/tech-doctolib/getting-hired/"> candidate experience page</a>.</p> <h2>&nbsp;</h2> <h2><strong>Job details</strong></h2> <ul> <li>Permanent position</li> <li>Tech stack: Python, Elasticsearch, Solr, Vertex AI, vector search, embeddings</li> <li>Full-time</li> <li>Levallois-Perret, France</li> <li>Hybrid work setup (up to 2 remot