Machine Learning Scientist I / II, Protein Design
About this role
Designing therapeutic molecules for active biologics programs forms the core of daily operations, partnering closely with domain scientists to translate complex targets and experimental constraints into actionable design hypotheses. The Life Sciences AI team builds models and systems that transition biologics from initial design specifications to wet-lab validated leads, integrating specialist design models directly into an autonomous science platform. Building scalable reasoning capabilities for drug discovery and maintaining robust evaluation infrastructure allows the team to continuously improve molecule design across multiple programs.
Succeeding in this role requires a strong blend of software engineering fundamentals, rigorous evaluation practices, and deep domain expertise in protein sequence, structure, and function. The position exists to bridge individual campaign work with reliable, extensible systems that generalize across therapeutic programs. Ideal candidates possess an exceptional talent for building and a solid biological intuition, translating empirical learnings into automated, reproducible decision-making workflows.
What you will do
- Design molecules for active biologics programs while partnering with domain scientists to translate biological targets and experimental constraints into actionable design hypotheses.
- Develop reasoning capabilities for drug discovery, which includes orchestrating complex design workflows.
- Design and maintain evaluation infrastructure and benchmarks to measure whether design workflows produce generalizable decisions across multiple programs.
- Own operational aspects related to reproducibility, throughput, and inference cost for computational design workflows.
- Collaborate with domain scientists to understand design prioritization and translate that judgment into machine learning objectives and evaluation criteria.
What you need
- Hold a Master of Science or Doctor of Philosophy degree in computer science, machine learning, computational biology, biophysics, bioengineering, or a related quantitative field.
- Demonstrate strong software engineering and system design fundamentals.
- Apply rigor in evaluation and dataset design, including understanding benchmark leakage, validation failures, and automated decision-making measurement.
- Communicate effectively across cross-functional teams and disciplines.
- Bring domain expertise focused on protein sequence, structure, and function.
Nice to have
- Experience building reasoning models, agents, planning systems, or multi-step ML orchestration.
- Exposure to designing antibodies, nanobodies, enzymes, peptides, or other therapeutic proteins within design-test-learn loops.
- Experience developing evaluation harnesses, model registries, or benchmark suites.
- Background in training or serving models at scale through distributed training, high-throughput inference, or GPU efficiency.
- Publications, open-source contributions, or applied research outputs in AI for Science venues.
Benefits
- Medical, dental, and vision coverage
- Employer-paid life and disability insurance
- Flexible time off with generous company-wide holidays
- Paid parental leave
- Educational assistance program and commuter benefits
- Company subsidized lunch program
Skills and tech stack
Questions candidates ask
What is the salary range for the role?
The expected base salary range for U.S.-based positions is $176,000 to $304,000 USD. Your final offer will reflect your background, expertise, and expected impact.
What kind of benefits are provided?
Full-time U.S. employees receive a comprehensive benefits program including medical, dental, and vision coverage; employer-paid life and disability insurance; flexible time off; and paid parental leave. Additional perks include an educational assistance program, commuter benefits, and a company subsidized lunch program.
What will I be working on day to day?
You will design molecules for active biologics programs and partner with domain scientists to translate constraints into design hypotheses. You will also develop reasoning capabilities for drug discovery and build benchmarks that measure generalizable decisions.
What background is required to apply?
Candidates must have an MS or PhD in computer science, machine learning, computational biology, biophysics, bioengineering, or a similar quantitative field. You also need strong software engineering fundamentals and domain expertise in protein sequence, structure, and function.