The Data Scientist / Research Developer will join the DME team, a transversal group working closely with Protein Vector Engineering and Computational Biology.

The role is primarily focused on data science and coding (Python), with a strong emphasis on:

• implementing and evaluating ML models,

• turning prototypes into clean, reusable code,

• helping to make data and models FAIR and systematic.

Biology knowledge is a strong plus but not strictly required; you will learn domain context on the job.

Core mission within the AI FAIR Lab:

• Work on data science tasks for internal projects related to gene and cell therapies (in collaboration with other data scientists and domain teams).

• Implement and maintain ML experiments in a reproducible way:data preprocessing, model training scripts, evaluation workflows.

• Help transform research prototypes (from notebooks) into: clean Python modules, small internal libraries or scripts that can be reused across projects.

• Contribute to the FAIR and systematisation work of the team by:

  • adding tests, logging and configuration to existing code,

  • refactoring models for reusability (e.g. moving from ad hoc code to parameterised functions/classes),

  • helping to standardise input/output formats.

• Participate in benchmarking and comparisons of different models/approaches:

  • setting up evaluation pipelines,

  • tracking metrics,

  • generating simple reports and visualisations.

• Collaborate with more senior team members (Senior Scientist, Head of DME team) to implement ideas from papers or internal proposals, iterate quickly on model and data improvements.

MSc with 1–2+ years of experience (internships can count if substantial).

PhD is a plus but not required.

Fields (or equivalent experience): Data Science, Computer Science, Applied Mathematics, Statistics, Machine Learning, or related quantitative disciplines.

Preferred experience with some of:

• End-to-end data science projects:

  • data cleaning, feature engineering, model training, evaluation and reporting.

• ML (classical and basic Deep Learning):

  • regression, classification, tree-based models;

  • basic neural networks.

  • Graph NN are a plus.

• Software development and scientific pipeline development: writing modular Python code, packaging utilities, working with Git, Docker.

• Working with real-world, messy data (any domain).

• *Biology / omics / healthcare data (*a plus, but not mandatory)

1. Entretien téléphonique avec Oscar (Head of DME)

2. Entretien visio avec l’équipe People & Culture

3. Cas technique a réaliser chez soi

4. Onsite meeting (présentation du cas technique et rencontre avec l’équipe