About the role
About CellType
CellType is building foundation models and agent systems for biology.
We believe the next major advances in biotech AI will come from rich biological data, strong model systems, and reliable infrastructure working together. We work with pharma and biotech partners on problems such as preclinical-to-clinical translation, response prediction, biomarker discovery, and scientific reasoning across complex biological datasets.
We are building the core intelligence layer for biology, and that requires a world-class data and ML platform.
About the role
We are hiring a Founding Platform Engineer to build the infrastructure backbone behind our training, evaluation, and inference stack.
We are looking for someone who can build the systems that make biological data usable for model development at speed and at scale: ingestion, indexing, search, retrieval, dataset interfaces, reproducibility, validation, orchestration, observability, and distributed performance.
You will work on the full path from raw data to training-ready datasets to reliable production workflows. The right person will make it dramatically easier for the rest of the team to build, evaluate, and ship models.
What you'll do
- Build and maintain data infrastructure for model training, evaluation, and inference
- Design and scale high-performance inference serving systems for biological foundation models
- Design standardized dataset interfaces so biological data is consistent, discoverable, and easy to use across the team
- Build ingestion and processing pipelines for public, proprietary, and customer datasets
- Build indexing, search, and retrieval systems that make large datasets queryable and useful in practice
- Establish safeguards and validation systems so datasets are reproducible, versioned, and trustworthy once standardized
- Improve throughput, latency, and reliability of distributed data loading and ML pipelines
