Skip to content

Doctolib

Staff AI Engineer - Agent Evaluation Platform (x/f/m)

Paris · posted 2026-11-19 · listed from another job board

Source: ASHBY

Sign up to apply

Share this job

At a glance

Workplace
Hybrid
Location
Paris
Region
Europe
Time zones
UTC+1
Employment type
Full time
Seniority
Mid senior
Skills
AI, CI/CD, ML, Python
Posted
2026-11-19

About the job

Join a team of passionate and hardworking entrepreneurs to transform healthcare!

Working in the tech team at Doctolib involves building innovative products and features to improve the daily lives of care teams and patients. We work in feature teams in an agile environment, while collaborating with product, design, and business teams.

WHAT YOU'LL DO

We are looking for a Staff AI Software Engineer to join the AI Evaluation team (EvalX) at Doctolib and help every AI product team measure, understand and improve the quality, reliability and safety of their systems.

Our AI products span patient-facing conversational agents, AI-powered phone assistants and clinical assistants supporting healthcare professionals. EvalX builds the platform, tools and methods that let these teams evaluate continuously, and our ambition is to make evaluation a core engineering practice.

In this role, you will work at the intersection of platform engineering, applied AI and product teams: you build shared evaluation capabilities, and you work directly with the teams that use them so they actually get adopted.

In this role, you will:

  • Design, ship, and operate production-grade evaluation tooling (APIs, services, CI/CD integrations) used by AI product teams across Doctolib
  • Work hands-on with product teams to assess how they evaluate today, define improvement plans, and help them own their evaluation quality
  • Design evaluation strategies for agentic systems, combining deterministic checks, LLM-as-a-judge, simulation-based testing, and human review
  • Build intelligent capabilities for production sampling, dataset representativeness monitoring, distribution-shift detection, and test case generation
  • Help teams define meaningful quality metrics, representative datasets, and reliable quality gates throughout the development lifecycle
  • Turn recurring product needs into reusable, self-service platform capabilities, and measure success through adoption, team autonomy, and evaluation coverage
  • Contribute to cross-functional initiatives that shape Doctolib's AI platform and best practices for building and evaluating agentic systems

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 could be our next team mate if you:

  • Have 6+ years of experience as a software engineer, with significant experience using Python; or as a machine learning engineer
  • Have built or operated evaluation for LLM-powered or agentic systems: datasets, LLM-as-a-judge, human review, production-driven evaluation
  • Understand and promote software development best practices
  • Are product-oriented and enjoy working directly with other teams, challenging assumptions, and turning complex needs into concrete solutions
  • Can influence engineering practices and drive change without hierarchical authority: your job is not done until your solution is adopted
  • Are comfortable speaking and writing in English in your day-to-day with the team

Now, it would be fantastic if you:

  • Have experience with applied ML techniques such as embeddings, clustering, statistical sampling, and distribution monitoring
  • Have experience building developer platforms or internal tooling, or in a Forward Deployed Engineering role
  • Have experience in the medical domain or another regulated environment

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 http://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
  • Enrollment in Doctolib's long-term employee value sharing plan called DoctoGrowth
  • ParentCare Program: Enjoy full salary coverage (100%) during your first month of birth leave, and 75% during the second, covered by Doctolib
  • For caregivers and workers with disabilities, a package including an adaptation of the remote policy, extra days off for medical reasons, and psychological support

The interview process

  • A first interview with a member of the Talent Acquisition team
  • A coding interview
  • An agentics system design
  • A behavioural interview
  • Reference check

JOB DETAILS

  • Permanent position
  • Full Time
  • Workplace: Levallois
  • Start date : As soon as possible

If you would like to find out more about tech life at Doctolib, feel free to read our latest Medium blog articles!

At Doctolib, we believe in improving access to healthcare for everyone - regardless of where you come from, what you look like. This translates into our recruitment process: Doctolib is an equal opportunity employ

More remote jobs at Doctolib

All 168 remote jobs at Doctolib

More jobs like this

Get matched to jobs like this

Free profile, one-click applications, and alerts for new roles.

Join free