Machine Learning Scientist I - Generative & Agentic AI for Drug Discovery

Frontier Medicines•South San Francisco, CA
•$100,000 - $158,900

About The Position

Frontier Medicines is seeking a Machine Learning Scientist to join its AI team in South San Francisco. The role builds AI systems for scientific research, including LLM-powered agents that work across research data, generative models for designing covalent molecules, and predictive models trained on proprietary covalent chemistry and chemoproteomics datasets. The position is suited to someone with a research mindset who wants their work to inform real decisions. The scientist will work in a small team with close communication with medicinal chemistry, biology, and computational chemistry. Prior drug discovery experience is not required; the company will teach the chemistry.

Requirements

  • MS or PhD in computer science, machine learning, computational chemistry, physics, or a related field, or a BS with 2–3 years of equivalent industry or research experience.
  • A track record of research, demonstrated through publications, preprints, thesis work, or substantial open-source contributions in machine learning.
  • Hands-on experience building with LLMs and agents, generative models, or multimodal models.
  • Strong Python and PyTorch skills, and comfort with modern AI coding tools.
  • Ability to turn an open-ended scientific problem into a working system, independently and collaboratively.
  • Clear written and verbal communication.
  • Legal authorization to work in the United States.

Nice To Haves

  • Experience with molecular machine learning, such as GNNs, equivariant models, or molecular representations, or with RDKit and cheminformatics tooling.
  • Experience with large-scale or distributed training, including DeepSpeed, FSDP, or MoE.
  • Exposure to biology, chemistry, or drug discovery data.

Responsibilities

  • Build agentic AI systems for scientific workflows, including multi-agent orchestration, tool calling and MCP integrations, task decomposition, and human-in-the-loop checkpoints, connected to scientific databases and the compound registry.
  • Develop and adapt generative models, including diffusion models, autoregressive transformers, and RL-guided generation, to explore new covalent chemical space.
  • Build multimodal models and RAG pipelines that reason over molecular structures, assay data, protein structures, slide decks, reports, and images.
  • Train and benchmark predictive models for property prediction, virtual screening, and SAR, including approaches for low-data settings such as transfer, multi-task, and active learning.
  • Deploy models and agents for researchers to use and contribute to active programs.

Benefits

  • Health care plan, including medical, dental, and vision.
  • Retirement plan, including 401(k) and IRA.
  • Life insurance, including basic, voluntary, and AD&D coverage.
  • Paid time off, including vacation, sick leave, and public holidays.
  • Family leave, including maternity and paternity leave.
  • Short-term and long-term disability.
  • Training and development.
  • Free food and snacks.
  • Wellness resources.
  • Stock option plan.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service