Senior Data Scientist
Core
Develop machine learning models to predict sequence-to-property relationships and guide construct selection for large-molecule discovery.
Role type
Senior IC data scientist (protein design & generative models)
Builds
Production ML models for biomolecular developability and structural tractability
Domain
Biopharma / Computational Biology / Protein Engineering
Deliverable
production ML models
Required skills
Python, PyTorch, protein language models, diffusion models, active learning, Bayesian optimization, uncertainty estimation, large-scale data processing, high-performance computing (via careerplan.io/jobs/R-248179-1-senior-data-scientist-at-amgen)
Preferred skills
Generative modeling, transfer learning, model validation, cloud platforms (AWS), reproducible ML practices, scientific publication record
Technologies
PyTorch, Python, numpy, scipy, pandas, AWS, Docker, Git
Responsibilities
Develop and apply ML models to predict sequence-to-property relationships; Build scalable data-processing and model-training workflows; Design and train foundation models (protein language models, diffusion models); Implement uncertainty-aware modeling approaches; Apply active learning and Bayesian optimization for experimental design; Collaborate with experimental teams to define objectives and interpret results
Seniority
Senior, hands-on IC
