Senior Data Scientist

Senior Data Scientist to join the AI & Data for Engineered Biologics team within Amgen's Large Molecule Discovery organization. In this role, you will advance data-driven prediction and design of fit-for-purpose proteins by developing ML models that connect sequence, structure, biophysical measurements, and experimental outcomes to biomolecular developability and structural tractability. Your work will reduce reliance on trial-and-error workflows, improve the probability of experimental success, and guide construct and condition selection for large-molecule discovery.

The successful candidate will work in a highly collaborative, multidisciplinary environment, partnering with protein scientists, structural biologists and ML engineers to support decisions from early design through sample generation and structural characterization.

What You'll Do

• Develop and apply machine learning models to predict sequence-to-property relationships.
• Develop scalable, reproducible data-processing, feature-generation, model-training, and evaluation workflows for large-scale biological datasets.
• Design, implement and train state-of-the-art foundation models including protein language models, diffusion models, or other generative approaches using multimodal biological data.
• Develop interpretable and uncertainty-aware modeling approaches that quantify confidence and support decision-making.
• Apply active learning and Bayesian optimization to guide experimental design and iterative improvement of protein design workflows.
• Collaborate cross-functionally with experimental teams to define modeling objectives, prioritize experiments, and interpret results.
• Communicate scientific findings clearly through presentations, written summaries and discussions with technical and non-technical stakeholders.

What We're Looking For

• Doctorate degree with 4+ yrs in Data Science, Computer Science, Computational Biology, Bioinformatics, Computational Chemistry, or a related field
• Or Master’s degree and 8+ years of directly related experience
• Experience developing predictive machine learning models for biological, structural, biophysical, or experimental outcome data.
• Strong programming skills in Python and experience with modern machine learning frameworks such as PyTorch
• Experience with Python scientific computing tools, such as numpy, scipy, pandas, etc.
• Experience with protein language models, representation learning, transfer learning, and generative modeling.