below marketmost similar roles pay hereabove market
This role pays more than
52%
of similar roles. Most pay
$162,000–$229,212
— the blue band above.
At the midpoint, this role pays about
$194k
versus about
$196k
for comparable roles.
Based on 240 similar postings.
Employer
About Gilead Sciences
Gilead Sciences, Inc. is a leading American biopharmaceutical company specializing in discovering, developing, and commercializing innovative medicines for unmet medical needs.
Gilead Sciences currently has
37 open roles
on FindRole.
Listed pay typically runs
$168,980–$218,680
across 28 roles with salary data.
The Senior Scientist, AI/ML (Biologics Design) joins the Research Data Sciences team to advance machine learning methods for designing and optimizing biologic therapeutics, including antibodies and multispecifics. This role involves developing novel AI approaches such as protein language models, structural learning, and generative modeling to guide molecule design and improve developability. The successful candidate will build predictive models linking sequence, structure, and experimental measurements to molecular properties while integrating diverse data sources like biophysical characterization and functional screening. Key technical requirements include a Ph.D. in a quantitative field, proficiency in Python, and experience with PyTorch or JAX. The work focuses on solving complex protein engineering problems by applying representation learning, geometric neural networks, and active learning strategies to accelerate candidate optimization within the biologics discovery pipeline.
Develop novel machine learning approaches to support biologics discovery and lead optimization.
Apply protein language models, foundation models, and representation learning methods for therapeutic protein design.
Build predictive models linking sequence, structure, and experimental measurements to key molecular properties.
Develop structure-aware learning approaches that incorporate protein conformation and molecular context.
Design and evaluate generative methods for exploring protein sequence space and proposing therapeutic candidates.
Integrate diverse data sources including biophysical characterization, developability assessments, and functional screening datasets.
Implement active learning and data-efficient modeling strategies for discovery programs with limited experimental data.
Contribute to the scientific direction of AI-enabled biologics design within Research Data Sciences.
What we're looking for
Ph.D. in Computational Biology, Machine Learning, Computer Science, Structural Biology, Biophysics, Bioengineering, or a related quantitative field.
Demonstrated experience developing and applying machine learning methods to biological or molecular problems.
Strong programming skills in Python and experience with modern ML frameworks such as PyTorch or JAX.
Experience building, training, and evaluating deep learning models, including representation learning, geometric learning, multimodal learning, or generative modeling.
Strong understanding of protein structure and sequence-function relationships.
Proven scientific productivity through publications, open-source contributions, or impactful research projects.
Excellent communication and collaboration skills within multidisciplinary scientific teams.
Experience with protein language models, AlphaFold-class models, antibody engineering, or modeling developability-related properties (preferred).
Machine Learning
Python
SQL
Feature Engineering
Model Deployment
Data Pipelines
Model Monitoring
Drift Detection
Statistics
Probabilistic Methods
Data Quality