ML Scientist I/II: Protein Design & Therapeutics AI

Lila Sciences; San Francisco (CA); On-site; USD 176,000 - 304,000; Full time

Benefits offered by this job

Comprehensive benefits

Equity

Job summary

Lila Sciences is seeking an ML Scientist I/II to advance AI-driven protein engineering at the intersection of machine learning and biology. You will design and evaluate ML workflows that guide design, screening, and learning from biomolecular data.

Collaboration with experimental and platform teams is essential to translate biology questions into computational objectives. The role emphasizes building scalable ML methods for de novo design, structure- and sequence-based prediction, and active

Qualifications

• PhD or equivalent in a quantitative field.
• Experience applying ML to protein design or biomolecules.
• Strong ML fundamentals and hands-on model development.
• Fluency with sequence, structure, function, developability, or experimental validation.

Responsibilities

• Build ML workflows for protein engineering campaigns from design to learning.
• Develop methods for de novo generation, property prediction, and active learning.
• Integrate design methods into robust software and reasoning models.
• Translate therapeutic questions into ML problems and evaluation plans.
• Collaborate with experimental scientists to interpret results and improve models.
• Create evaluation frameworks for model generalization to complex biologics.

Skills

Protein design ML

ML fundamentals

Biomolecular data

Design problem formulation

Collaboration skills

Education

PhD in Computational Biology/CS/ML/Biophysics/Bioengineering

Job description

Lila Sciences is seeking an ML Scientist I/II to advance AI-driven protein engineering at the intersection of machine learning and biology. You will design and evaluate ML workflows that guide design, screening, and learning from biomolecular data.

Collaboration with experimental and platform teams is essential to translate biology questions into computational objectives. The role emphasizes building scalable ML methods for de novo design, structure- and sequence-based prediction, and active