New: upload your resume and get matched to AI jobs. Free to start →

Research Engineer, Chemical, Biological and Nuclear AI Safety

$174k - $252k • Mountain View, CA, USA • Full-time

Posted 1mo ago

Job Location

Mountain View, CA, USA

Also open in London, UK

Tech Stack

Remote Work Policy

On-site

Employment Type

Full-time

Categories

AI Engineer

About the job

Google's Responsible Frontier Artificial Intelligence Research team is focused on ensuring that as AI models like Gemini advance in scientific capabilities, they do not become instruments of catastrophic harm. This role involves applied research, writing production code, and deploying safeguards to a vast user base. The position is not suited for those primarily seeking to publish research or engage in purely policy-focused work. Expect rigorous data management, demanding release schedules, and participation in an on-call rotation. You will engage with technical discussions on mass-casualty threats and their prevention, meticulously investigating minor discrepancies that could indicate significant issues. Your work will range from designing new safeguards to diagnosing unexpected evaluation outcomes or proactively testing system vulnerabilities.

Responsibilities

  • Develop and test new safeguards using automated and manual red teaming, assessing their impact on legitimate scientific research.
  • Design, implement, and execute evaluations for risks related to chemical, biological, radiological, nuclear, and explosives in advanced models, including agentic systems.
  • Oversee the reliability of critical systems, encompassing safeguards and incident response.
  • Collaborate with scientific experts to translate their insights into datasets and automated grading tools, managing sensitive data under stringent security protocols.
  • Report findings, including uncertainties and negative results, to technical teams and leadership.

Requirements

  • Bachelor's degree in a Management, Scientific, Technical, or Engineering field, or equivalent practical experience.
  • 5 years of experience writing code in a shared, version-controlled codebase with other contributors, including research software.
  • 3 years of experience training, fine-tuning, or evaluating machine learning models.
  • Master's degree or PhD in Chemistry, Physics, Chemical, Nuclear Engineering, Biology, or a Computational Science.
  • Experience building classifiers or evaluation infrastructure for large language models.
  • Experience applying statistics to machine learning evaluation.
  • Experience running software in production, including monitoring, on-call or incident response.
  • Experience in chemical, biological, radiological or nuclear security, export control, or adversarial work such as red teaming, security research or abuse prevention.

Benefits

  • 15% bonus target
  • Equity
  • Benefits

About Google DeepMind