Co-op, AI for Protein Design

Lila Sciences • San Francisco, CA

2d

About The Position

This PhD-level co-op will join Lila Sciences’ Life Science AI team to contribute to applied machine learning research in protein engineering, including generative protein design, antibody engineering, developability, and wet-lab-informed model iteration. Working with Lila scientists and ML researchers, the co-op will explore generative and predictive models for protein sequence, structure, and function; analyze biological and experimental datasets to evaluate model outputs; and prototype workflows connecting model predictions, candidate prioritization, and wet-lab feedback. The role also involves building datasets and benchmarks that support domain-specific protein design models and general AI research models. Results will be communicated through code, notebooks, written summaries, and presentations.

The position is intended for a currently enrolled PhD student in computer science, machine learning, computational biology, bioengineering, biophysics, or a related field, with research experience in machine learning or protein engineering, strong Python skills, and experience with frameworks such as PyTorch or JAX. Familiarity with protein language models, diffusion or flow-based models, antibody design, or active learning workflows is a plus.

The role supports Lila Sciences’ mission of combining automated data generation with scientific superintelligence. Lila describes its work as building systems that learn for themselves, combining advanced AI models with proprietary AI Science Factory instruments to execute the scientific method autonomously and accelerate discovery across medicine, materials, and energy.

Requirements

• Currently enrolled PhD student in computer science, machine learning, computational biology, bioengineering, biophysics, or a related field.
• Research experience in machine learning, computational biology, or protein engineering.
• Strong Python skills and experience with PyTorch, JAX, or similar frameworks.
• Experience working with biological sequence, structure, or assay data.
• Clear communication skills and comfort collaborating with cross-disciplinary teams.

Nice To Haves

• Experience with protein language models, structure prediction, or generative design, including diffusion or flow-based models.
• Familiarity with antibody design, developability, or wet-lab validation concepts.
• Publications, preprints, or open-source work in machine learning for biology.

Responsibilities

• Research generative and predictive models for protein and antibody design.
• Analyze experimental datasets to evaluate model outputs and guide design decisions.
• Prototype workflows linking model predictions, candidate prioritization, and wet-lab feedback.
• Build datasets and benchmarks that support domain-specific protein design models and general AI research models.
• Communicate results through code, notebooks, written summaries, and presentations.

What This Job Offers

• Career Level: Intern
• Education Level: Ph.D. or professional degree