Scale AI - San Francisco, CA

posted 4 days ago

Full-time - Senior
San Francisco, CA
Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services

About the position

As a Research Scientist focused on Frontier Risk Evaluations, you will design and create evaluation measures, harnesses and datasets for measuring the risks posed by frontier AI systems. For example, you might do any or all of the following: Design and build harnesses to test AI agents for dangerous capabilities such as hacking or exploiting security vulnerabilities; Develop and run human-in-the-loop tests of AI capabilities to deceive, manipulate, blackmail, or otherwise engage in social engineering; Work with government agencies or other labs to collectively scope and design evaluations to measure and mitigate risks posed by advanced AI systems.

Responsibilities

  • Design and build harnesses to test AI agents for dangerous capabilities such as hacking or exploiting security vulnerabilities.
  • Develop and run human-in-the-loop tests of AI capabilities to deceive, manipulate, blackmail, or otherwise engage in social engineering.
  • Work with government agencies or other labs to collectively scope and design evaluations to measure and mitigate risks posed by advanced AI systems.

Requirements

  • Commitment to our mission of promoting safe, secure, and trustworthy AI deployments in the industry as frontier AI capabilities continue to advance.
  • Practical experience conducting technical research collaboratively, with proficiency in frameworks like Pytorch, Jax, or Tensorflow.
  • A track record of published research in machine learning, particularly in generative AI.
  • At least three years of experience addressing sophisticated ML problems, whether in a research setting or in product development.
  • Strong written and verbal communication skills to operate in a cross functional team.

Nice-to-haves

  • Hands-on experience with open source LLM fine-tuning or involvement in bespoke LLM fine-tuning projects using Pytorch/Jax.
  • Experience in crafting evaluations or a background in data science roles related to LLM technologies.
  • Experience working with cloud technology stack (eg. AWS or GCP) and developing machine learning models in a cloud environment.

Benefits

  • Comprehensive health, dental and vision coverage
  • Retirement benefits
  • Learning and development stipend
  • Generous PTO
  • Commuter stipend (may be eligible)
Job Description Matching

Match and compare your resume to any job description

Start Matching
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service