ML Scientist I/II, AI for Protein Engineering
About this role
Translating computational biomolecule design into wet-lab-validated leads remains a core bottleneck in modern medicine, and this hire will directly address that challenge by building advanced machine learning workflows for protein engineering campaigns. Within the Life Sciences AI group at Lila Sciences, this team develops generative and predictive models that bridge in silico hypotheses and experimental biology. The person joining this group will design, evaluate, and iterate on AI methods spanning de novo generation, property prediction, and active learning while collaborating closely with experimental scientists and software engineers.
Operating at the intersection of machine learning, protein engineering, and therapeutic design, the successful candidate brings strong technical fundamentals alongside a deep curiosity for protein biology. Day-to-day work involves translating biological objectives into precise computational problems, integrating design methods into broader reasoning models, and interpreting experimental outcomes to drive continuous model refinement. Someone with a collaborative mindset, rigorous quantitative training, and a genuine interest in computationally designed biologics will thrive in this environment.
What you will do
- Build machine learning workflows for protein engineering campaigns spanning from initial design specifications through experimental learning cycles.
- Develop and adapt modern AI methods that cover de novo generation, sequence- and structure-based property prediction, candidate selection, and active learning.
- Integrate protein design methodologies directly into robust software systems and broader autonomous science reasoning models.
- Translate complex therapeutic and biological questions into well-defined machine learning problems, model outputs, and structured evaluation plans.
- Partner directly with experimental scientists to analyze why designed biomolecules succeed or fail, utilizing those insights to improve model performance.
- Construct evaluation frameworks that measure model generalization capabilities when applied to challenging biologics design problems.
What you need
- Hold a PhD in Computational Biology, Computer Science, Machine Learning, Biophysics, Bioengineering, or a related quantitative academic field.
- Bring practical experience applying machine learning techniques specifically to protein design, biologics engineering, or closely related biomolecular design problems.
- Demonstrate strong machine learning fundamentals supported by hands-on background in developing, adapting, training, or evaluating modern artificial intelligence methods.
- Maintain fluency with biological sequence, structure, function, developability considerations, and experimental validation principles.
- Possess the ability to translate therapeutic or biological objectives into actionable computational design problems and comprehensive evaluation plans.
- Exhibit strong collaboration and communication skills to work effectively across machine learning, biology, experimental science, and software engineering teams.
Nice to have
- Experience designing antibodies, nanobodies, enzymes, peptides, or other therapeutic proteins.
- Experience with structure prediction, generative protein design, diffusion models, flow matching, or protein language models.
- 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.
- Industry experience translating machine learning research into practical biological design workflows, experimental campaigns, or platform capabilities.
- Publications, open-source contributions, or applied research outputs in AI for science venues.
Benefits
- Comprehensive medical, dental, and vision coverage
- Employer-paid life and disability insurance
- Flexible time off with generous company-wide holidays
- Paid parental leave and an educational assistance program
- Commuter benefits, including bike share memberships for office-based employees
- Company subsidized lunch program
Skills and tech stack
Questions candidates ask
What is the compensation range for this role?
The expected base salary range for U.S.-based positions is $176,000 to $304,000 USD. The final offer will reflect your background, expertise, and expected impact alongside bonus potential and early-stage equity.
What kind of team will I be working with?
You will sit at the intersection of machine learning, protein engineering, and therapeutic design. You’ll collaborate closely with experimental scientists, AI researchers, and platform teams to build models and workflows.
What types of technologies and methods are used?
The work involves generative and predictive models, de novo generation, sequence- or structure-based property prediction, candidate selection, and active learning. Bonus areas include diffusion models, flow matching, and protein language models.
Where is the position located?
The role is located in San Francisco, CA, USA, with office-based perks including commuter bike share memberships and a company subsidized lunch program.