Teams at Biohub

Build and scale frontier AI systems for biology: design model architectures, run large-scale pretraining on GPU clusters, develop RL/reward modeling and multi-agent systems, create evaluation frameworks tied to biological outcomes, and publish/open-source research.

Develop and maintain analysis workflows and visualization tools for spatiotemporal multi-omics datasets; integrate proteomics and metabolomics; apply machine learning approaches; collaborate with experimental teams and contribute to publications and open-source software.

Lead design of genomic data representations and tokenization for biological AI models; define data standards and quality metrics; integrate heterogeneous modalities into training frameworks; evaluate representation impacts on model performance; partner with ML engineers and researchers; lead cross-functional data initiatives; drive data acquisition and generation; mentor senior contributors.