Doctolib logo

Doctolib

More roles at Doctolib

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

Hybrid

Part remote, part office, you need to live within commuting distance of a named location.

Hybrid · Paris

Employer listed it 4 months ago · Added 2 months ago

Been open since 4 months ago. Long-running listings are sometimes left up after the role is filled.

Salary

Not stated

Location

Hybrid · Paris

Timezone

Not stated

Contract

Full-time

Experience

Lead

Category

Data

The employer did not publish a salary, and we have too few comparable roles to estimate one.

What the advert says

Quoted word for word from the employer's advert. Where it says nothing, we say so.

Working hours
Not mentioned in the advert
Where you can work from
Hybrid work setup (up to 2 remote days per week)
Contract
Permanent position
Experience asked for
Not mentioned in the advert
Pay
Lunch vouchers (Swile card) worth €8.50 per working day, with €4.50 covered by Doctolib

Remote flexibility

Hybrid

This role is only partly remote, the employer expects time in the office around Paris, Hybrid, so you need to live within commuting distance.

What the employer says

  • Source listing states candidate location: "Paris, Hybrid"
  • Listing mentions "Hybrid"

What Nomaders makes of it

  • Not suitable if you plan to move between countries

The quotes above are the employer's own words; the reading is ours. Always check the original listing and employment terms before working from another country.

Before you apply

Questions worth asking: Nomaders interpretation

  • This role involves office time, but the advert does not say how often. Ask how many days a week are expected on site.

Produced automatically from this advert's text; not reviewed by a person. The employer's own page is the final word.

About the role

Set a new pulse for healthcare!

We are looking for several Staff Machine Learning Engineers - Retrieval to join two AI teams that ground Doctolib's AI in trusted medical knowledge:

Medical Knowledge Platform grounds clinical decision support for health professionals in validated sources: HAS guidelines, learned society recommendations and peer-reviewed clinical studies, across more than 100 million documents.

Ground makes sure the answers of Doctolib's patient assistant, a conversational system of about twenty agents, rest on reliable medical knowledge.

In both teams, retrieval quality directly affects 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 retrieval systems that ground AI answers in validated medical sources, for health professionals or for patients

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

Operate at scale: architect and optimise systems for demanding volume and latency, up to 100M+ documents, 50+ req/s and sub-300 ms latency on the clinical side

Build custom re-rankers, optimise 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

Design offline and online evaluations and controlled experiments around what actually helps users, and decide when retrieval is the right tool and when another grounding approach works better

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

Help the engineers around you get better at retrieval

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 and retrieval systems used by real users in a 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, optimised indexing pipelines, or engineered query processing solutions that required real technical depth

Bring statistical rigour to evaluation and design experiments that measure real user value

Are pragmatic and product-minded: you work closely with product managers and take your work all the way to production

Requirements

The employer hasn't listed requirements separately, they're described in the role summary above and on the original listing.

Benefits

  • ·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

How to apply

  1. 1Check the flexibility label above, hybrid, matches where you plan to live and work.
  2. 2Tailor your CV to the role at Doctolib, mentioning your remote working experience.
  3. 3Apply directly on the employer's careers page using the button below. Nomaders never handles your application.

Found 2mo ago. Last checked today. Always confirm the details on the original posting, salary and location can change after publication.

Listing sourced from Company boards.

Similar roles

Other open data roles with comparable remote rules.

Browse all open roles

Pay not stated · You'll be taken to the employer's careers page.