Principal Scientist, Machine Learning and Computational Biology

Moderna•Cambridge, MA
•$158,600 - $285,500•Onsite

About The Position

Moderna is seeking a scientifically rigorous and collaborative Principal Scientist to develop next-generation computational and machine-learning approaches for individualized cancer immunotherapies within Cancer Vaccines and Bioinformatics Research. The role will help advance cancer vaccine design by identifying opportunities for algorithmic innovation and developing machine-learning methods to improve antigen selection. The successful candidate will define modeling strategies, data requirements, and validation frameworks; develop novel computational methods; and address scientific and technical challenges at the intersection of immunology, machine learning for biology, and predictive algorithm development. They will work closely with computational, experimental, statistical, and translational colleagues to turn biological insights into algorithmic improvements, while providing technical leadership and mentorship across the team. The position is 100% onsite. Moderna describes its work environment as smoke-free, alcohol-free, and drug-free.

Requirements

  • PhD in Computer Science, Statistics, Machine Learning, Computational Biology, or a related discipline.
  • At least five years of post-PhD experience, preferably in industry, with demonstrated expertise developing and applying modern machine-learning approaches to complex biological, biomedical, or molecular data.
  • Thorough knowledge of modern machine-learning architectures and tools.
  • Ability to independently define scientific problems, develop novel computational approaches, and critically evaluate model performance, robustness, and generalization.
  • Experience integrating and learning from heterogeneous, noisy, incomplete, or high-dimensional biological datasets.
  • Expert programming skills in Python and knowledge of modern machine-learning frameworks and scalable computational environments.
  • Ability to partner effectively with scientific collaborators and translate biological questions into computational strategies.
  • Strong scientific communication skills and a track record of influencing technical or scientific direction through rigorous analysis.
  • Eligibility to access export-controlled information under U.S. law; only U.S. persons (citizens, permanent residents, asylees, or refugees) are eligible for this position.

Nice To Haves

  • Experience with biological modeling, including protein or nucleotide language models, transfer learning, contrastive learning, or generative modeling.
  • Experience developing predictive models for complex biological processes and integrating experimental measurements with machine-learning models to guide future data generation.
  • Experience providing cross-functional technical mentorship and scientific leadership in multidisciplinary research environments.
  • Familiarity with cancer immunology, antigen processing and presentation, T-cell biology, or computational immunology.
  • Familiarity with statistical approaches for uncertainty quantification, experimental design, and evaluation of incremental data value.
  • Track record of scientific impact through influential publications, presentations, collaborations, patents, or development of novel computational methods.

Responsibilities

  • Contribute to scientific, computational, and machine-learning methodology for next-generation neoantigen selection and identify high-impact opportunities for algorithmic innovation.
  • Develop novel predictive models, biological representations, learning strategies, and computational methodologies as a hands-on technical leader.
  • Define modeling approaches, training data requirements, and validation strategies aligned with scientific and program objectives.
  • Establish rigorous evaluation strategies to measure model generalization, robustness, calibration, and performance in biologically meaningful settings.
  • Partner with experimental and translational scientists to define fit-for-purpose training labels, characterize assay and data quality, and identify experimental datasets with potential to improve predictive models.
  • Design and guide prospective validation studies to assess the downstream impact of algorithmic improvements.
  • Evaluate emerging AI/ML approaches and external technologies for their potential to improve antigen selection and vaccine design.
  • Provide technical leadership and mentorship to computational scientists and help translate research advances into robust computational improvements.

Benefits

  • Competitive healthcare and voluntary benefit programs.
  • Access to fitness, mindfulness, and mental health support.
  • Family planning benefits, including fertility, adoption, and surrogacy support.
  • Paid time off, including vacation, volunteer days, sabbatical, global recharge days, and a discretionary year-end shutdown.
  • Savings and investment programs.
  • Location-specific perks and extras.
  • Potential eligibility for an annual discretionary bonus, other incentive compensation, or an equity award, subject to plan eligibility criteria and individual performance.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service