Research Scientist, Interpretability of LLMs

Company: Google DeepMind
Location: Seattle
Posted on: March 9, 2025

Job Description:

SnapshotAdvances research in understanding large language models by considering controllability as a dual problem with understanding.About UsWe are a team in Google DeepMind, with a mission to build AI responsibly to benefit humanity. Our team pursues practical interpretability; interpretability not for the sake of explanation, but for it to be directly useful for something. Our current focus for this 'something' is controllability. We use controllability as a way to evaluate interpretability; if we can use explanations to do something useful with the model, chances are that the explanation bears some faithfulness.The RoleResearch scientist role to advance research in understanding large language models by considering controllability as a dual problem.Key Responsibilities:

• Conduct research in understanding the model with practicality as a focus.
• Translate research findings into useful internal applications.
• Publish and present findings at internal and external venues to influence the field.About YouIn order to set you up for success as a Research Scientist at Google DeepMind, we look for the following skills and experience:
  • PhD in machine learning, statistics or related fields.
  • Strong publication record.
  • Strong record in LLMs and foundation models and related engineering skills.In addition, the following would be an advantage:
    • Strong end-to-end system building and prototyping skills.The US base salary range for this full-time position is between $136,000 - $300,000 + bonus + equity + benefits. Your recruiter can share more about the specific salary range for your targeted location during the hiring process.At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law. If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.
      #J-18808-Ljbffr

Keywords: Google DeepMind, Seattle , Research Scientist, Interpretability of LLMs, Other , Seattle, Washington