AI Safety & Privacy Research Scientist

Meta

San Francisco (CA)

On-site

USD 122,000 - 181,000

Full time

22 hours ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Bonus
Equity
Benefits

Job summary

Meta's FAIR Security, Privacy, and Reliability team is hiring an AI Research Scientist to explore safety, security, and robustness issues in foundational models. The role focuses on discovering novel failures, developing benchmarks, and designing post-training mitigations to advance production-grade AI systems.

Candidates will collaborate across teams to translate research into scalable solutions, contribute to evaluation reports, and publish results in top venues.

Qualifications

  • PhD in CS, ML or related field, or equivalent practical experience.
  • Research experience in safety, security, privacy, or robustness of AI models.
  • Experience with adversarial ML and prompts/jailbreaks discussed.
  • Ability to develop mitigations and evaluate foundation models.

Responsibilities

  • Conduct fundamental research to discover safety and security failures in AI models.
  • Develop benchmarks for Meta's foundational model evaluation suite.
  • Design post-training mitigations for safety, privacy, and reliability risks.
  • Collaborate with cross-functional teams to translate research into production.

Skills

Adversarial ML
Robustness testing
Memorization risk analysis
Safety and privacy research

Education

PhD in Computer Science or related field
Bachelor's in CS/CE or equivalent

Job description

Meta's FAIR Security, Privacy, and Reliability team is hiring an AI Research Scientist to explore safety, security, and robustness issues in foundational models. The role focuses on discovering novel failures, developing benchmarks, and designing post-training mitigations to advance production-grade AI systems.

Candidates will collaborate across teams to translate research into scalable solutions, contribute to evaluation reports, and publish results in top venues.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

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
AI Safety Researcher: Frontier Mitigations
AI Safety Researcher: Frontier Mitigations

OpenAI, Inc. • San Francisco (CA)

On-site
GBP 120,000 - 180,000
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
Research Scientist – AI Safety Red Teaming
Research Scientist – AI Safety Red Teaming

MetaSense Inc • Menlo Park (CA)

On-site
USD 184,000 - 257,000
Lead AI Safety Researcher for Frontier Models
Lead AI Safety Researcher for Frontier Models

Alice • San Francisco (CA)

On-site
USD 180,000 - 280,000
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
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
GenAI Safety & Alignment Research Scientist
GenAI Safety & Alignment Research Scientist

DeepMind Technologies Limited • New York (NY)

On-site
USD 207,000 - 300,000
Senior AI Safety & Fairness Researcher — Remote
Senior AI Safety & Fairness Researcher — Remote

MaziCTools • Los Angeles (CA)

Hybrid
USD 41,000 - 56,000
Head of AI Safety Research
Head of AI Safety Research

Far Ai • Berkeley (CA)

Hybrid
USD 150,000 - 210,000
Health Insurance
Retirement - 401(k) plan with up to 2%
PTO - 25 days Paid Time Off per year
+3