Staff AI Safety Engineer - Red Team & Guardrails

B Capital

San Francisco (CA)

On-site

USD 120,000 - 160,000

Full time

14 days+
Application generator

An application made for this job — a tailored resume and cover letter that speak straight to the posting.

Get past ATS filters

Benefits offered by this job

Top-tier compensation
Comprehensive medical, dental, vision, life, and disability insurance
Fully paid parental leave
Paid time off
Daily lunch and dinner provided

Job summary

B Capital in San Francisco is looking for individuals passionate about AI safety to own the red-teaming and adversarial evaluation pipeline for their models. The role involves collaborating with the Alignment team and ensuring all releases meet safety thresholds.

Candidates should have a graduate degree in Computer Science or a related field, exceptional knowledge of LLM safety, and a willingness to make high-stakes decisions. B Capital offers a competitive compensation package and comprehensive health benefits.

Qualifications

  • Graduate degree or equivalent experience in AI Safety.
  • Deep understanding of adversarial attacks and red-teaming methodologies.
  • Experience in building automated evaluation pipelines.

Responsibilities

  • Own the red-teaming and adversarial evaluation pipeline for models.
  • Work with Alignment team to translate safety findings into guardrails.
  • Validate releases against the lab’s risk thresholds.

Skills

Technical understanding of LLM safety
Software engineering capabilities
Experience with Reinforcement Learning
Ability to thrive in a startup environment

Education

Graduate degree (MS or PhD) in Computer Science, Machine Learning

Job description

B Capital in San Francisco is looking for individuals passionate about AI safety to own the red-teaming and adversarial evaluation pipeline for their models. The role involves collaborating with the Alignment team and ensuring all releases meet safety thresholds.

Candidates should have a graduate degree in Computer Science or a related field, exceptional knowledge of LLM safety, and a willingness to make high-stakes decisions. B Capital offers a competitive compensation package and comprehensive health benefits.

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Open-Model AI Safety Lead: Red Team & Validation | Equity
Open-Model AI Safety Lead: Red Team & Validation | Equity

Reflection AI • New York (NY)

On-site
USD 180,000 - 240,000
Top-tier compensation
Comprehensive medical, dental, and vision insurance
Fully paid parental leave
+2
Senior AI Red Team Scientist for Safety & Evaluation
Senior AI Red Team Scientist for Safety & Evaluation

SupportFinity™ • New York (NY)

On-site
USD 190,000 - 211,000
401(k) plan
Bonus program
Equity opportunity
Remote AI Safety Red Teamer (Contract)
Remote AI Safety Red Teamer (Contract)

United States Digital Space LLC • United States

Remote
USD 96,000 - 116,000
AI/LLM Safety Engineer — Guardrails & Red Teaming
AI/LLM Safety Engineer — Guardrails & Red Teaming

Propio • United States

Remote
USD 90,000 - 130,000
AI Safety Red Teamer Expert
AI Safety Red Teamer Expert

Obsidian • New York (NY)

On-site
USD 170,000 - 260,000
AI Safety Red Team Engineer
AI Safety Red Team Engineer

Anthropic • San Francisco (CA)

Hybrid
USD 320,000 - 405,000
AI Safety Red Teamer Expert
AI Safety Red Teamer Expert

Mercor • New York (NY)

On-site
USD 150,000 - 190,000
Cyber Red Team Specialist: AI Safety & Adversary Testing
Cyber Red Team Specialist: AI Safety & Adversary Testing

OpenAI • Washington

Hybrid
USD 180,000 - 280,000
Relocation assistance
Hybrid work model
AI Safety Red Teamer Expert
AI Safety Red Teamer Expert

Obsidian • San Francisco (CA)

On-site
USD 150,000 - 230,000
AI Safety Red Team Specialist (Remote)
AI Safety Red Team Specialist (Remote)

Mercor • San Francisco (CA)

On-site
USD 90,000 - 130,000