Empirical AI Safety Researcher

Redwood Research

Berkeley (CA)

On-site

USD 120,000 - 180,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Redwood Research is seeking an empirical researcher to design and run experiments on frontier language models, assessing AI risks and evaluating safety measures. You will work with a small, rigorous research team to generate evidence-based insights that inform responsible AI development.

The role emphasizes careful experimentation, result documentation, and collaboration with cross-disciplinary colleagues. A four-month work trial may precede full-time advancement during the hiring process.

Qualifications

  • Familiarity with AI safety concepts and threat models.
  • Experience running frontier LLM experiments.

Responsibilities

  • As an empirical researcher, you will design and run experiments on frontier language models to assess AI risks and test the safety measures meant to address them.

Skills

Basic familiarity with AI safety andth
Basic familiarity with running modernf

Job description

Redwood Research is seeking an empirical researcher to design and run experiments on frontier language models, assessing AI risks and evaluating safety measures. You will work with a small, rigorous research team to generate evidence-based insights that inform responsible AI development.

The role emphasizes careful experimentation, result documentation, and collaboration with cross-disciplinary colleagues. A four-month work trial may precede full-time advancement during the hiring process.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Empirical Researcher
Empirical Researcher

Redwood Research • Berkeley (CA)

On-site
USD 120,000 - 180,000
AI Safety Researcher: Red-Teaming, Safe RLHF, Unlimited PTO
AI Safety Researcher: Red-Teaming, Safe RLHF, Unlimited PTO

Bison • San Francisco (CA)

On-site
USD 350,000 - 475,000
Health benefits
Dental benefits
Vision benefits
+3
Conceptual Reasoning Researcher: AI Risk & Theory
Conceptual Reasoning Researcher: AI Risk & Theory

Aisafety • Berkeley (CA)

On-site
USD 90,000 - 150,000
Conceptual Reasoning Researcher for AI Safety & Theory
Conceptual Reasoning Researcher for AI Safety & Theory

Redwood Research • Berkeley (CA)

On-site
USD 90,000 - 150,000
Frontier-Model Safety Researcher & Evaluations
Frontier-Model Safety Researcher & Evaluations

OpenAI • San Francisco (CA)

Hybrid
USD 380,000 - 500,000
Relocation assistance
Hybrid work model
AI Safety Researcher (Fully Remote)
AI Safety Researcher (Fully Remote)

Trajectory Labs, PBC • United States

Remote
USD 83,000 - 152,000
Research Engineer: Frontier AI Risk & Standards
Research Engineer: Frontier AI Risk & Standards

Artificial Intelligence Underwriting Company • San Francisco (CA)

On-site
USD 180,000 - 280,000
Annual salary
Equity
Health insurance
+2
AI Safety Research Scientist: Red Teaming & Innovation
AI Safety Research Scientist: Red Teaming & Innovation

Meta • New York (NY)

On-site
USD 184,000 - 257,000
AI Safety Researcher — Investigate Model Behavior & Impact
AI Safety Researcher — Investigate Model Behavior & Impact

Typesafe AI, Inc. • San Francisco (CA)

On-site
USD 180,000 - 240,000
AI Safety Research Scientist - Red Team Leader
AI Safety Research Scientist - Red Team Leader

MetaSense Inc • Menlo Park (CA)

On-site
USD 184,000 - 257,000