About The Position

The Frontier Research team within AI for Drug Discovery advances fundamental machine learning and statistics methods motivated by real-world challenges in drug discovery. The team addresses important biology and medicine problems that cannot be solved with off-the-shelf machine learning, developing novel solutions and new ways of framing problems. Its work focuses on long-horizon research that can support multiple internal and external applications. The Machine Learning Scientist will develop methods and frameworks for uncertainty quantification, statistical inference, and experimental design to guide decision-making across the drug-discovery pipeline. The role contributes to research projects that produce conference and journal publications and open-source code, supports cross-organizational collaborations and applications, and disseminates knowledge through internal and external scientific conferences. The scientist will collaborate with colleagues in South San Francisco, New York, and Basel, Switzerland.

Requirements

  • Must be pursuing, or have completed within the last 12 months, a Ph.D. in Computer Science, Statistics, Applied Mathematics, Physics, Computational Biology, or a related technical field; equivalent research productivity is also accepted.
  • Demonstrated expertise in a paradigm of uncertainty quantification for decision-making, such as sequential or online statistical inference, experimental design, conformal prediction, reinforcement learning, calibration, or game-theoretic statistics.
  • Proven publication record and experience contributing to the research community, including at conferences such as NeurIPS, ICML, ICLR, AISTATS, or UAI, and/or relevant journals.
  • Excellent technical writing and communication skills, as well as collaboration and interpersonal skills.

Nice To Haves

  • Experience developing machine-learning and/or statistical methods for biological or clinical data.
  • Experience developing open-source packages.

Responsibilities

  • Develop methods and frameworks for uncertainty quantification, statistical inference, and experimental design, informed by problem settings in machine-learning-guided drug discovery.
  • Contribute to and drive research projects resulting in conference and/or journal publications and open-source code.
  • Foster cross-organizational collaborations and applications.
  • Present research and expertise at internal and external scientific conferences.
  • Collaborate with team members in South San Francisco, New York, and Basel, Switzerland.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service