# Founding Research Scientist, Biological Foundation Models at CellType

- Company: CellType (YC W26)
- What the company does: The agentic drug company. We simulate human biology. Backed by Y Combinator.
- Company website: https://www.celltype.com
- Type: Startups (AI role)
- Level: Mid level
- Location: New York, NY, US
- Work setup: On-site
- Pay: $150K to $250K base salary per year (USD)
- Posted: 2026-09-07
- Apply by: 2026-10-22
- Apply: https://www.ycombinator.com/companies/celltype/jobs/ynLk0Xr-founding-research-scientist-biological-foundation-models
- Page: https://www.1752.vc/careers/jobs/celltype-founding-research-scientist-biological-foundation-models/

## About the role

We are hiring a Founding Research Scientist to own the modeling in our biology programs end to end. This is the role that turns a partner's scientific question into a model task, a dataset, an evaluation, and a result a pharma team will act on. You will work directly with the founders on the projects that define the company over the next year, and you will have a lot of room to decide how we model biology, not just implement someone else's plan.

## What they're looking for

- Own modeling for one or more live pharma and biotech programs: framing the problem, choosing the representation and architecture, building the training and evaluation loop, and delivering results to the partner
- Train, fine-tune, and post-train biological foundation models on single-cell, perturbation, spatial, multi-omic, imaging, and clinical assay data
- Build models of cellular state and response: perturbation prediction, in-silico screening, cross-species and cell-line-to-patient translation, deconvolution, and related virtual-cell tasks
- Design evaluations that biologists trust: held-out perturbations, unseen cell types and tissues, cross-species and cross-cohort generalization, and wet-lab-in-the-loop validation with our partners
- Decide what data to acquire or generate next, and shape the data-generation experiments we run with academic and pharma collaborators
- Turn one-off project results into reusable model capabilities and product workflows

Tags: Engineering