Senior ML Scientist, AI for Protein Engineering

Lila Sciences•San Francisco, CA

12d•$268,000 - $358,000

About The Position

Lila is building a platform where AI and automation co-evolve to solve the hardest problems in medicine. Within Life Sciences AI, the AI for Protein Engineering team develops and applies generative and predictive models that move biomolecule design programs from in silico hypothesis to wet-lab validated leads. We are looking for a senior individual contributor focused on computational biologics design. The work spans active protein engineering programs and new capabilities that improve how Lila designs, evaluates, and learns from biomolecular sequence, structure, and function data. This role sits at the intersection of machine learning, protein engineering, and therapeutic design. The ideal candidate brings deep ML judgment, intuition for protein biology, and experience delivering computationally-designed, wet-lab-validated biologics through AI. You’ll collaborate with experimental scientists, AI researchers, and platform teams to connect specialist protein design models into Lila’s broader autonomous science platform.

Requirements

PhD in Computational Biology, Computer Science, Machine Learning, Biophysics, Bioengineering, or a related quantitative field.
Strong track record applying machine learning to protein design, biologics engineering, or related biomolecular design problems, with industry experience strongly preferred.
Deep ML expertise, with hands-on experience adapting and developing modern AI methods rather than only applying them off the shelf.
Strong intuition for therapeutic biologics design, including sequence, structure, function, developability, and experimental validation considerations.
Demonstrated ability to drive applied research independently, from problem definition through experimental validation and iteration.
Strong collaboration and communication skills across ML, biology, experimental science, and software teams.

Nice To Haves

Direct experience designing antibodies, nanobodies, enzymes, peptides, or other therapeutic proteins for applied or clinical pipelines.
Experience with structure prediction, generative protein design, diffusion models, flow matching, or protein language models in a production research setting.
Familiarity with structural biology, conformational dynamics, developability, affinity maturation, or other biophysical constraints.
Experience closing design-test-learn loops with wet-lab teams, including experimental prioritization, high-throughput validation, and active learning.
Publications, open-source contributions, or applied research outputs in AI for science venues.

Responsibilities

Own applied ML workflows for protein engineering campaigns, from design specification through experimental learning.
Develop and adapt methods spanning de novo generation, sequence- or structure-based property prediction, candidate selection, and active learning. Integrate these methods into robust software systems and broader reasoning models.
Translate therapeutic and biological questions into well-defined ML problems, model outputs, and evaluation plans.
Partner with experimental scientists to interpret why designed biomolecules succeed or fail, then turn those insights into better models and design principles.
Build rigorous evaluation frameworks for model generalization to challenging biologics design problems.