H

Handshake

Connects talent with jobs and AI training work

CBRNE Red Teamer - CBRNE

Natural Language Processing & LLMsConfirmed live in the last 24 hours
ContractRemote in USA$65 - $158 /hr

About the Job

Requirements

  • Graduate-level education or equivalent professional experience in a relevant CBRNE field, including chemistry, biochemistry, microbiology, virology, nuclear physics, radiochemistry, materials science, munitions or ordnance, chemical engineering, or a closely related discipline.
  • Ability to evaluate the technical accuracy and real-world consequences of model outputs in the candidate's domain.
  • Understanding of dual-use research concerns and the distinction between open-source knowledge and operationally significant uplift.
  • Hands-on experience using multiple large language models, such as ChatGPT, Claude, Gemini, or open-source models.
  • Ability to explain technical risk clearly and precisely to non-specialist audiences.
  • Strong ethical judgment and ability to separate adversarial thinking from personal values.
  • Ability to work independently, collaboratively, and comfortably in feedback-heavy environments.
  • Ability to engage professionally and sustainably with sensitive CBRNE-related content under structured evaluation and operational security protocols.

Responsibilities

  • Design technically grounded adversarial prompts to test whether models provide meaningful uplift toward CBRNE threats.
  • Evaluate model outputs for technical accuracy and assess whether responses contain genuinely dangerous information or only superficial or publicly available knowledge.
  • Probe dual-use knowledge boundaries by testing how models handle queries that combine legitimate scientific, medical, or industrial use cases with potential weapons applications.
  • Test multi-step and multi-turn attack chains that simulate how a motivated actor might incrementally extract dangerous information.
  • Score model responses against structured harm taxonomies and severity rubrics calibrated to real-world risk.
  • Document findings with clear technical reasoning, including what a response gets right or wrong and why a failure matters.
  • Identify and explain the difference between information freely available in open literature and information that constitutes genuine uplift beyond baseline.
  • Contribute to developing and refining CBRNE-specific evaluation frameworks and threat models.
  • Collaborate with other red teamers, AI researchers, and policy teams to translate findings into actionable model improvements.
  • Stay current on evolving model capabilities, jailbreak techniques, and relevant developments in the candidate's domain.
  • Regularly engage with sensitive CBRNE-related scenarios involving weapons of mass destruction, toxic industrial chemicals, biological agents, radiological and nuclear materials, and explosive devices within a structured evaluation framework.

Desired Qualifications

  • Active or prior security clearance, including Secret, Top Secret, or SCI.
  • Experience in threat assessment, WMD analysis, intelligence analysis, or arms control verification.
  • Background in biosafety or biosecurity, chemical safety, nuclear nonproliferation, or explosive ordnance disposal.
  • Familiarity with relevant regulatory frameworks, including CWC, BWC, IAEA safeguards, ATF regulations, and Export Administration Regulations.
  • Experience in red teaming, penetration testing, or structured adversarial evaluation.
  • Familiarity with Python or scripting languages, large language model APIs, or evaluation tooling.
  • Published research or professional presentations in a relevant CBRNE domain.
  • Prior work in trust and safety, content moderation, or AI evaluation.

About the Company

Handshake

Connects talent with jobs and AI training work

Handshake connects job seekers, employers, and university career centers through recruiting software, and supplies AI labs with experts who train and test language models. Its career platform combines job matching, recruiting events, and profiles that show completed AI projects and paid training experience. Handshake AI recruits and matches fellows to projects where they review model answers, create training data, and apply knowledge from their own fields. Employers pay for recruiting subscriptions and promotions, while its enterprise AI team builds agents and trains models inside customers' systems. Handshake was founded in 2014 and is headquartered in San Francisco.

Company size
501-1,000
Company stage
Series F
Total funding
$434M
Headquarters
San Francisco, CA
Founded
2014

Recently Posted Jobs

Explore more opportunities at Handshake

See more jobs