Member of Technical Staff, Post-Training

About the role

As a Member of Technical Staff, Post-Training you will develop training and evaluation loops that shape biological world models after pretraining, bridging fundamental research and practical engineering.

Key responsibilities

• Develop and tune post‑training recipes, including datasets, reward signals and hyperparameters for biological models.
• Design and build evaluation suites for biological reasoning, long‑context behavior, robustness and model reliability.
• Debug end‑to‑end model behavior, investigate failure modes and trace issues to data, optimization or systems.
• Explore preference‑ and feedback‑driven learning methods such as preference modeling and reward modeling.
• Curate high‑quality post‑training datasets, including expert‑informed and synthetic data.
• Study scaling effects of dataset size, recipe complexity and compute budget to guide future directions.

Required profile

• Strong track record in ML research or engineering, especially in frontier‑model training, post‑training or alignment.
• Proficiency in building production‑quality software and research infrastructure, ideally in Python and PyTorch.
• Ability to design careful experiments, interpret ambiguous results and separate real effects from artifacts.
• Excellent written and verbal communication skills for cross‑disciplinary collaboration.
• Curiosity, rigor and a bias toward iterative improvement.

Required skills

• Python
• PyTorch

What we offer

• Competitive compensation and comprehensive benefits.
• Support for continual learning and professional development.
• Opportunity to work on cutting‑edge AI for biology in a collaborative, cross‑disciplinary environment.