G

Goodfire

Public-benefit AI interpretability lab building models

Forward Deployed Research Scientist - Life Sciences

AI ResearchConfirmed live in the last 24 hours
Full-timeSan Francisco, CA, USA

About the Job

Requirements

  • PhD, MD, or equivalent experience in biology, with a strong machine learning background and experience in computational biology or bioinformatics.
  • Deep familiarity with large models and a passion for understanding how they work.
  • Fluency in Python and machine learning frameworks such as PyTorch.
  • Strong writing and communication skills for explaining complex ideas.
  • Drive to move quickly and take ownership.

Responsibilities

  • Lead scientific research with partners to interpret advanced biological foundation models, including genomic foundation models, vision transformers, and protein language models, to uncover what they have learned.
  • Own research delivery on high-stakes customer projects, including defining problems and hypotheses, sourcing data, building tools, iterating, and implementing solutions.
  • Translate research into tools for real-world applications in precision medicine, digital pathology, drug discovery, and other areas.
  • Work directly with customers to conduct original research in interpretability and computational biology.
  • Prototype techniques to visualize and manipulate internal model structures.
  • Collaborate with engineering to turn research into production-ready tools.
  • Drive partnership success by collaborating closely with customers and partners.
  • Help define and evolve the research direction.

Desired Qualifications

  • Experience leading research in a forward deployed environment and in service of customer requirements.
  • Familiarity with interpretability, alignment, or safe model development.
  • Experience in startup or fast-paced lab environments.

About the Company

Goodfire

Public-benefit AI interpretability lab building models

Goodfire is a public-benefit AI interpretability lab in San Francisco that provides a model-design environment to understand, edit, debug, and monitor foundation models rather than treating them as black boxes. Its platform lets teams inspect model decisions, apply interpretability-informed training to reduce errors, and test and monitor changes across deployments. It differentiates itself through its public-benefit mission, collaborations with Arc Institute, Mayo Clinic, and Microsoft, and leadership with researchers, having halved LLM hallucinations and reverse-engineered a biological model to identify Alzheimer's biomarkers. Its goal is to make foundation models safer, more understandable, and easier to manage at scale by promoting transparency and accountability in AI development and deployment.

Company size
51-200
Company stage
Series B
Total funding
$207M
Headquarters
San Francisco, CA
Founded
2024

Recently Posted Jobs

Explore more opportunities at Goodfire

See more jobs