Research Scientist, Virtual Cell Modelling & Perturbative Biology Foundation Models

Valence Labs•Montreal, QC

7d•Hybrid

About The Position

You will be joining a research program building multimodal foundation models to predict cellular responses to chemical and genetic perturbations across petabyte-scale omics and imaging data. The work spans generative and distributional modeling, representation learning for molecules and genes/proteins, and the design of biologically grounded evaluation frameworks. The goal is to close critical gaps in the pre-clinical pipeline, replacing or augmenting wet-lab perturbation screens with in silico predictions that are reliable enough to drive drug discovery decisions. We are seeking a Research Scientist with strong ML research and engineering skills, and genuine curiosity for biology, to join a multidisciplinary team of ML researchers, engineers, and computational biologists working toward a shared goal: building virtual cells that transform how medicines are discovered.

Requirements

PhD (or equivalent) with significant academic or industry research experience in machine learning applied to drug discovery, life sciences or other real-world scientific or engineering problems.
Strong background in generative modeling and representation learning, with experience applying these to high-dimensional scientific data (e.g., images, count matrices, graphs); experience with biological data is a plus.
Scientific knowledge of biology or chemistry, with familiarity with perturbational / interventional experimental paradigms (e.g., chemical or genetic screens, transcriptomics, high-content imaging).
Impactful research track record, including developing ML models for complex real-world data, proposing new training or evaluation approaches, or applying generative methods to scientific problems, particularly in biology or life sciences.
Strong technical and engineering skills, including the ability to rapidly prototype and scale ML models, manage large codebases, and maintain reproducible research pipelines; Python proficiency required, experience with compiled languages a plus.
Cross-functional comfort, with the ability to work effectively across disciplines (e.g with dry and wet-lab scientists) to ensure models address real scientific questions.
Leadership and communication skills: including an authorship record in peer-reviewed conferences (e.g., NeurIPS, ICML, ICLR) or journals (e.g., Nature, Science, Cell).

Nice To Haves

Exceptional ML candidates willing to develop biological expertise on the job.
Experience with biological data is a plus.
Experience with compiled languages a plus.

Responsibilities

Research and develop generative and distributional models (e.g., flow matching, diffusion models) to predict high-dimensional cellular responses.
Build and maintain ML systems capable of processing massive multiomics datasets on high-performance compute clusters.
Work closely with colleagues to ensure model predictions are interpretable, trustworthy, actionable, and grounded in real experimental outcomes.
Help design and implement rigorous evaluation metrics that test generalization across for cellular context, unseen perturbations and covariates, going beyond IID performance to reflect real deployment conditions.
Publish findings in top-tier venues (e.g., NeurIPS, ICML, Nature, Science, Cell) and contribute to the broader scientific community.