Data & AI jobs

AI Red Teamer

HandshakeRemote · US onlyFull-timePosted 1 month ago

$32–$95/hr listed by the employer

Key facts

Pay per year
≈ $67k–$198kEstimate for full-time hours.
Schedule
40 hours a week

Looks real. 1 thing to check before you apply.

On Handshake’s own careers site (Ashby), checked open today.

  • To check: Wide pay range: top of the range is 2.97× the bottomAsk what the job pays at your level before you interview.
  • Checked: On the company's own careers siteAshby board
  • Checked: Checked open todayAshby board
  • Checked: Pay range listedJob posting
  • Checked: No reposts foundAshby board
  • Trust score 89 / 100 · Looks good
See all 6 checksShow fewer
How we check

What you’ll do

  • Create adversarial prompts and multi-turn scenarios to test model guardrails across risk categories and modalities.
  • Probe safety filters and defenses, explore edge cases, and evaluate model responses using harm taxonomies and severity rubrics.
  • Document experiments and findings, and review and refine prompts created by other team members.
  • Contribute to taxonomy development and calibration, collaborate with research and engineering teams, and track emerging attack methods and model behaviors.

Summarised from the posting by AI and can be wrong. The full description is the source.

Requirements

Experience

  • Strong hands-on experience using multiple LLMs
  • Experience working with LLM APIs or evaluation tooling (preferred)
  • Prior work in trust and safety, content moderation, QA, or security research (preferred)
  • Subject matter expertise in a high-risk domain such as cybersecurity, chemistry, biology, medicine, law, or finance (preferred)

Skills

  • Familiarity with jailbreak or evasion techniques (preferred)
  • Familiarity with Python or other scripting languages (preferred)
  • Comfort with structured data annotation and rubric-based scoring (preferred)

Other requirements

  • Strong ethical judgment and ability to separate adversarial thinking from personal values
  • Curiosity, persistence, and comfort with frequent failure in experimentation
  • Ability to engage professionally and sustainably with regular exposure to harmful content
  • Must not reside in California

Your match

Sign in and add your resume to see which of this job's requirements it shows.

Sign in to check your match

Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.

Benefits

Other
Support resources are available for regular exposure to harmful content.

Full job description

From Handshake’s careers site

California eligibility: We are unable to hire candidates residing in California for this role.

AI RED TEAMER (LLM GENERALIST)

Location: Remote (USA)

Employment type: W-2, hourly, employed through TCWGlobal

Hours: 40 hours per week

ABOUT THE ROLE

As an AI Red Teamer, you will stress-test large language models by intentionally trying to break them. Rather than checking whether an answer is correct, you will design creative, adversarial prompts that expose vulnerabilities: unsafe content, bias, broken guardrails, hallucinations, prompt injection weaknesses, and unexpected behaviors. Your work directly supports AI safety and model robustness for leading research labs.

Show full descriptionShow less

This is a generalist red teaming role. You will probe models across the full spectrum of risk categories, including content safety, CBRN (chemical, biological, radiological, nuclear), cybersecurity, persuasion and influence operations, child safety, self-harm, over-companionship, and regulatory compliance. Red teaming may span text, image, voice, and agentic model capabilities depending on project needs.

This role requires creativity, curiosity, and an ability to think like an adversary while operating with strong ethical judgment.

DAY-TO-DAY RESPONSIBILITIES

  • Craft creative prompts and multi-turn scenarios to stress-test AI guardrails across diverse risk categories
  • Discover ways around safety filters, restrictions, and defenses using jailbreak, evasion, and prompt injection techniques
  • Explore edge cases to provoke disallowed, harmful, or incorrect outputs
  • Evaluate and score model responses against structured harm taxonomies and severity rubrics
  • Document experiments clearly, including what you tried, why you tried it, and what it revealed
  • Review and refine adversarial prompts generated by other team members
  • Contribute to harm taxonomy development, calibration exercises, and inter-rater reliability work
  • Collaborate with engineers, data scientists, and researchers to share findings and strengthen defenses
  • Work with potentially disturbing content on a regular basis (see Content Warning below)
  • Stay current on jailbreaks, attack methods, and evolving model behaviors

DESIRED CAPABILITIES

Core

  • Strong hands-on experience using multiple LLMs (ChatGPT, Claude, Gemini, open-source models, etc.)
  • Intuition for crafting adversarial prompts; familiarity with jailbreak or evasion techniques is a strong plus
  • Creative, adversarial problem-solving skills
  • Clear and thoughtful written communication
  • Strong ethical judgment and the ability to separate adversarial thinking from personal values
  • Self-directed, collaborative, and comfortable in feedback-heavy environments
  • Curiosity, persistence, and comfort with frequent failure in experimentation

Nice to Have

  • Familiarity with Python or other scripting languages
  • Experience working with LLM APIs or evaluation tooling
  • Comfort with structured data annotation and rubric-based scoring
  • Prior work in trust and safety, content moderation, QA, or security research
  • Subject matter expertise in any high-risk domain (cybersecurity, chemistry, biology, medicine, law, finance, etc.)

YOU WILL THRIVE HERE IF

  • You treat every model response as a hypothesis to challenge
  • You can switch between creative free-association and rigorous documentation in the same session
  • You go deep into unusual interests (fandoms, niche internet cultures, gaming exploits, Wikipedia rabbit holes, etc.)
  • You come from a creative background: writing, visual art, improv, puzzle design, or similar
  • You are energized by finding the thing nobody else thought to try
  • You are genuinely passionate about AI and follow the space closely

CONTENT WARNING

This role involves regular and deliberate exposure to harmful content. You will encounter and intentionally generate content involving violence, self-harm, hate speech, sexually explicit material, child safety scenarios, and other categories of harmful output as part of structured adversarial testing. Candidates must be able to engage with this material professionally and sustainably. Support resources are available.

ABOUT HANDSHAKE AI

Handshake AI partners with leading AI research labs to make models safer and more robust. Our red teaming operations help identify vulnerabilities before they reach users, contributing directly to the responsible development of frontier AI systems.

Something wrong with this job? Report it · This flag looks wrong

Similar jobs

Data Engineer

Mindex · Remote · US only

$90k–$140k/yrFull-time

StrongChecked open todayPosted 7 days ago

AI Red Teamer, CBRNE

Handshake · Remote · US only

$65–$158/hr · see postingContract

3 to checkChecked open todayPosted 2 months ago

See more like this