Senior AI/ML Scientist - Biologics Design

Gilead Sciences Inc.; Foster City (CA); On-site; USD 169,000 - 219,000; Full time

Benefits offered by this job

Annual bonus

Stock-based long-term incentives

Paid time off

Medical insurance

Dental insurance

Vision insurance

Life insurance

Job summary

Gilead Sciences Inc. in the United States seeks a Senior Scientist in AI/ML for Biologics Design to advance machine learning methods for designing and optimizing biologic therapeutics, including antibodies and multispecifics, using protein language models, structural learning, and generative approaches.

The ideal candidate will combine ML expertise with a passion for protein therapeutics and translating computational innovations into experimental impact.

Qualifications

• Ph.D. in a quantitative field required.
• Experience applying ML to biological problems.
• Strong programming skills in Python and ML frameworks.

Responsibilities

• Develop ML approaches for biologics discovery and lead optimization.
• Apply protein language models and representation learning for design.
• Build predictive models linking sequence, structure and measurements.
• Develop structure-aware learning with protein conformation and context.
• Design generative methods to explore protein space for candidates.
• Integrate diverse data sources including biophysical data and screenings.
• Implement active learning for data-efficient discovery programs.
• Collaborate with engineers, biologists, and researchers to drive decisions.
• Contribute to AI-enabled biologics design direction.

Skills

Python

PyTorch

JAX

Machine learning

Protein structure/sequence knowledge

Collaboration

Education

Ph.D. in Computational Biology, ML, CS, Structural Biology, Biophysics, Bioengineering or related field

Tools

PyTorch/JAX

Job description

Gilead Sciences Inc. in the United States seeks a Senior Scientist in AI/ML for Biologics Design to advance machine learning methods for designing and optimizing biologic therapeutics, including antibodies and multispecifics, using protein language models, structural learning, and generative approaches.

The ideal candidate will combine ML expertise with a passion for protein therapeutics and translating computational innovations into experimental impact.