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

Doctolib; Levallois-Perret; Hybride; EUR 120 000 - 180 000; Plein temps

Avantages offerts par ce poste

Health insurance

Vacation 25 days

Remote work 2 days/wk

Relocation support

Lunch vouchers

Résumé du poste

Doctolib is seeking a Staff Machine Learning Engineer - Retrieval to build and scale the Medical Knowledge Platform, grounding clinical AI decisions in HAS guidelines and medical studies. You will own the retrieval stack in a cross-functional team across Europe, shaping the future of healthcare AI.

You will work with vector embeddings, indexing pipelines, re-ranking, and deep RAG systems to deliver fast, reliable clinical search experiences for health professionals and patients.

Qualifications

• Proven production experience building and scaling search and retrieval systems in high-traffic environments.
• Full ownership of offline indexing and online retrieval pipelines.
• Hands-on with the retrieval tech stack: Elasticsearch, Solr, vector search and embeddings.
• Experience at a Senior or Staff level with autonomy and depth.

Responsabilités

• Own and scale Doctolib’s Medical Knowledge Platform, grounding AI decisions in medical sources and studies.
• Design and maintain indexing pipelines and end-to-end retrieval stacks.
• Achieve sub-300ms latency with systems handling 100M+ documents and 50+ req/s.
• Build and optimize re-rankers and query processing, plus evaluation frameworks.
• Develop deep Retrieval/ RAG systems, including vector embeddings and query rewriting.

Connaissances

Search & retrieval systems

Production-grade systems

Senior/Staff level

Distributed computing

Outils

Elasticsearch

Solr

Vertex AI

Vector search

Embeddings

Description du poste

Set a new pulse for healthcare!

We are looking for a Staff Machine Learning Engineer - Retrieval to join our AI team working on Clinical decision support and Medical Knowledge.

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 Medical Knowledge Platform , 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.

Working in the tech team at Doctolib means building innovative products and features to improve the daily lives of care teams and patients.

What you’ll do

Your responsibilities include but are not limited to:

• 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)

• Design and maintain both indexing pipelines and retrieval systems, ensuring end-to-end ownership across the full retrieval stack

• Operate at scale: architect and optimize systems handling 100M+ documents, 50+ req/s, and sub-300ms latency requirements

• Build custom re-rankers, optimize query processing pipelines, and design robust retrieval evaluation frameworks

• Engineer deep RAG systems from the ground up - going well beyond off-the-shelf components to tackle real medical knowledge complexity

• Work across the full retrieval stack: vector embeddings, vector search, re-ranking, query expansion and rewriting

Who you are

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.

You’ll be a great fit if you:

• Have proven production experience building and scaling search & retrieval systems in a real-world, high-traffic environment

• Bring deep dual expertise in both offline indexing and online retrieval; you own the full pipeline, not just one side of it.

• Are genuinely hands‑on with the retrieval tech stack: Elasticsearch, Solr, Vertex AI, vector search, embeddings, re‑ranking and query processing.

• Have gone beyond commodity RAG; you’ve built custom re‑rankers, optimized indexing pipelines, or engineered query processing solutions that required real technical depth.

• Have operated at Senior or Staff level, with the autonomy and technical depth that comes with it.

It would be fantastic if you:

• Have experience working with medical knowledge sources, clinical databases, or healthcare information systems

• Have contributed to evaluation frameworks and benchmarks for retrieval quality or AI outputs in regulated or high‑stakes environments

• Have worked in a multi‑lingual retrieval context or with domain‑specific ontologies

Life at Doctolib Tech

• 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.

• Our stack is composed of Rails, TypeScript, Java, Python, Kotlin, Swift, and React Native.

• We leverage AI ethically across our products to empower patients and health professionals. Discover our AI vision here.

Want to learn more about our tech culture and environment? Visit the Doctolib Tech site.

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 through our partner Moka.care

• Work from abroad for up to 10 days per year thanks to our flexibility days policy

• Lunch vouchers (Swile card) worth €8.50 per working day, with €4.50 covered by Doctolib

• A subsidy from the work council to refund part of the membership to a sport club or a creative class

• 50% reimbursement of your public transport subscription

• ParentCare Program: Enjoy full salary coverage (100%) during your first month of birth leave and 75% during the second, covered by Doctolib

• Enrollment in Doctolib’s long‑term employee value sharing plan called DoctoGrowth

• For caregivers and workers with disabilities, a package including an adaptation of the remote policy, extra days off for medical reasons, and psychological support

• Relocation support in case of international mobility

• Access to the best AI tools for coding, development and dedicated training

Our interview process

• Recruiter Screen (45’)

• Live Coding Interview (75’)

• System Design Interview (75’)

• Behavioural Interview (75’)

• Reference Check & Offer

We want your experience to be clear, respectful, and transparent. Learn more about our hiring process on our candidate experience page.

Job details

• Permanent position

• Tech stack: Python, Elasticsearch, Solr, Vertex AI, vector search, embeddings

• Full-time

• Levallois‑Perret, France

• Hybrid work setup (up to 2 remote days per week)

• Start date: as soon as possible

We welcome everyone

At Doctolib, we are committed to improving access to healthcare for everyone. This translates into our recruitment process. We evaluate candidates based solely on qualifications and motivation, without any form of discrimination.

The more diverse ideas are heard, the more our product will truly improve healthcare for all. You are welcome to apply to Doctolib, regardless of your gender, religion, age, sexual orientation, ethnicity, or disability.

To ensure equal opportunities, we invite you to exclude personal information (e.g., pictures, age) from your applications. If you require any accommodation, please let us know for support during the hiring process.

Join us in building the healthcare we all dream of!

Your data privacy

All information provided is processed by Doctolib for application management. For data processing details, click ici. Please contact hr.dataprivacy(at)doctolib.com for inquiries or to exercise your rights.