Remote CBRNE AI Red Teamer - Threat Modeling & Safety

Handshake

United States

Remote

USD 140,000 - 210,000

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

Benefits offered by this job

Remote work in the United States

Job summary

Handshake is seeking a remote, US-based CBRNE Red Teamer to rigorously evaluate AI models for dangerous uplift and safety guardrail failures. The role emphasizes ethical scrutiny, threat modeling, and collaboration with AI researchers and policy teams.

You will design adversarial prompts, assess technical accuracy and risk, and document findings with clear reasoning to drive model improvements and safer deployments.

Qualifications

  • Advanced degree in a CBRNE field or equivalent experience.
  • Ability to assess model outputs for technical risk and safety implications.
  • Experience with multiple LLMs and evaluation frameworks.
  • Strong written communication and ethical judgment.
  • Familiarity with threat modeling and dual-use research issues.

Responsibilities

  • Design adversarial prompts to test model responses to CBRNE threats.
  • Evaluate outputs for technical accuracy and risk.
  • Probe dual-use boundaries and uplift beyond baseline.
  • Test multi-step attack chains to simulate threat actor behavior.
  • Document findings with clear reasoning and actionable fixes.
  • Collaborate with AI researchers and policy teams.
  • Stay current on jailbreak techniques and evaluation tools.
  • Communicate risk to non-specialist audiences.

Skills

CBRNE domain expertise
Adversarial testing
Ethical judgment
Technical writing
LLM experimentation

Education

Graduate degree or equivalent in CBRNE

Tools

Python scripting
LLM APIs
Evaluation tooling

Job description

Handshake is seeking a remote, US-based CBRNE Red Teamer to rigorously evaluate AI models for dangerous uplift and safety guardrail failures. The role emphasizes ethical scrutiny, threat modeling, and collaboration with AI researchers and policy teams.

You will design adversarial prompts, assess technical accuracy and risk, and document findings with clear reasoning to drive model improvements and safer deployments.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

CBRNE AI Safety Red Teamer
CBRNE AI Safety Red Teamer

Handshake • United States

Remote
USD 140,000 - 210,000
AI Red Teamer, CBRNE (Remote)
AI Red Teamer, CBRNE (Remote)

Handshake • United States

Remote
USD 140,000 - 210,000
Remote work in the United States
Remote AI Safety Red Teamer (Contract)
Remote AI Safety Red Teamer (Contract)

Mercor • San Francisco (CA)

Hybrid
GBP 72,000 - 86,000
Remote AI Red Teamer: LLM Safety & Adversarial Testing
Remote AI Red Teamer: LLM Safety & Adversarial Testing

Handshake AI • United States

Remote
USD 55,000 - 110,000
AI Red Teamer: Offensive Security for AI Systems (Remote)
AI Red Teamer: Offensive Security for AI Systems (Remote)

Handshake • United States

Remote
USD 150,000 - 210,000
Remote AI Safety Red Teamer
Remote AI Safety Red Teamer

mercor • United States

Remote
USD 96,000 - 116,000
AI Safety Biosecurity SME: CBRNE Expert (Remote)
AI Safety Biosecurity SME: CBRNE Expert (Remote)

HireArt, Inc. • Dallas (TX)

Hybrid
USD 120,000 - 150,000
Remote work
Flexible schedule
96 hours PTO per year
+2
AI Red Teamer: Offensive Security & Threat Modeling
AI Red Teamer: Offensive Security & Threat Modeling

Handshake • United States

Remote
USD 140,000 - 210,000
Health Insurance
401k match
Parental leave
+1
AI Safety Red-Team Specialist — Remote Part-Time
AI Safety Red-Team Specialist — Remote Part-Time

Vettedlance • United States

Remote
USD 83,000 - 124,000
AI Safety Red Team Expert: Behavioral Health & Model Eval
AI Safety Red Team Expert: Behavioral Health & Model Eval

Auraone • United States

Remote
USD 62,000 - 96,000