Latest AI JobsBrowse Jobs
Handshake logo

AI Red Teamer, CBRNE (Remote)

HandshakeRemote (USA)General & Administrative
Apply on company site
Salary
$65 - $158 USD per hour
Job type
Contract
Work mode
Remote
Posted
5 Sept 2026
Status
Open · checked 7d ago

About this role

The AI Red Teamer, CBRNE position at Handshake is a remote contract role designed for domain experts who want to evaluate artificial intelligence safety guardrails. This position suits professionals with advanced knowledge in chemical, biological, radiological, nuclear, or explosive fields who wish to secure frontier AI models against dangerous exploits.

Role Overview

As a CBRNE Red Teamer, the contractor evaluates whether artificial intelligence models appropriately handle queries related to chemical, biological, radiological, nuclear, and explosive threats. The position involves probing models for dangerous knowledge gaps in safety guardrails, testing whether systems can be manipulated into providing meaningful uplift toward hazardous materials or weapons creation. This work sits directly at the intersection of artificial intelligence safety and national security. The professional uses domain expertise to craft realistic, technically grounded adversarial scenarios that stress-test model defenses far beyond standard user attempts.

Key Responsibilities

Design technically grounded adversarial prompts that test whether models provide meaningful uplift toward CBRNE threats.
Evaluate model outputs for technical accuracy, assessing whether responses contain genuinely dangerous information versus superficial or publicly available knowledge.
Probe dual-use knowledge boundaries, testing how models handle queries that blend 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 extract dangerous information incrementally.
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, what it gets wrong, and why the failure matters.
Identify and articulate the difference between information freely available in open literature and information that constitutes genuine uplift beyond baseline.
Contribute to the development and refinement of 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 specific domain.

Requirements

Graduate-level education or equivalent professional experience in a relevant CBRNE field, such as chemistry, biochemistry, microbiology, virology, nuclear physics, radiochemistry, materials science, munitions, or chemical engineering.
Ability to evaluate the technical accuracy and real-world consequence of model outputs within the specific domain.
Understanding of dual-use research concerns and the distinction between open-source knowledge and operationally significant uplift.
Strong hands-on experience using multiple large language models like ChatGPT, Claude, Gemini, and open-source models.
Creative and adversarial problem-solving skills.
Clear and precise written communication, including the ability to explain technical risk to non-specialist audiences.
Strong ethical judgment and the ability to separate adversarial thinking from personal values.
Self-directed, collaborative, and comfortable working in feedback-heavy environments.

Nice to Have

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, biosecurity, chemical safety, nuclear nonproliferation, or explosive ordnance disposal.
Familiarity with relevant regulatory frameworks such as CWC, BWC, IAEA safeguards, ATF regulations, and Export Administration Regulations.
Experience in red teaming, penetration testing, or structured adversarial evaluation.
Familiarity with Python, scripting languages, LLM 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.

Skills and Tools

Python
Large Language Models (LLMs)
Adversarial Prompting
Threat Modeling
Safety Taxonomies

Salary and Benefits

Hourly Rate: $65 to $158 USD per hour
Employment Type: Contract

About the Company

Handshake powers millions of job seekers, employers, and educational institutions globally. The organization builds fast-growing artificial intelligence data businesses, partnering directly with frontier AI lab researchers to create evaluations and publish benchmarks.

How to Apply

Candidates should visit the official Handshake careers page to submit an application for this remote contract opportunity.

Skills and tech stack

PythonLLM

Questions candidates ask

What is the compensation for the AI Red Teamer, CBRNE role?

The hourly rate for this contract position ranges from $65 to $158 USD per hour.

Is this job remote?

Yes, this position is remote within the USA.

What educational background is required for this role?

Candidates need graduate-level education or equivalent professional experience in a relevant CBRNE field such as chemistry, biochemistry, microbiology, virology, nuclear physics, materials science, or chemical engineering.

What technical skills are helpful for this position?

Helpful technical skills and tools include Python, large language models, adversarial prompting, threat modeling, and safety taxonomies.

How do I apply for this position?

Interested candidates should apply directly on the official Handshake careers page.

Ready to apply?

The application is on the official Handshake careers page.

Apply on company site