About the role
You will research, prototype, evaluate, and improve large-scale deep learning models for biomolecular and protein design. You will build pretraining infrastructure, curate evaluation datasets, analyze computational approaches, present findings, and collaborate across machine learning and protein design disciplines.
Responsibilities
- Design and develop autoregressive, diffusion, and representation-learning models for protein design
- Adapt and improve pretraining techniques for biomolecular deep learning models
- Architect, implement, and optimize infrastructure for pretraining protein language models
- Curate datasets and design evaluation tasks for generative models
- Implement, analyze, interpret, and present computational approaches
Requirements
- PhD or equivalent industry experience in a relevant technical or scientific field
- Experience conceiving, implementing, and evaluating novel machine learning and pretraining large-scale models in the biomolecular domain
- Publications at major machine learning conferences or scientific journals, or experience pretraining LLMs at frontier AI/ML labs
- Experience with PyTorch or JAX
- Legal authorization to work in the United States
Benefits
- Equity participation
- 401(k) with employer match
- Health, dental, and vision insurance
- Generous PTO policy
Requirements
- PhD or equivalent industry experience in a relevant technical or scientific field
- Experience conceiving, implementing, and evaluating novel machine learning and pretraining large-scale models in the biomolecular domain
- Publications at major machine learning conferences or scientific journals, or experience pretraining LLMs at frontier AI/ML labs
- Experience with PyTorch or JAX
- Legal authorization to work in the United States