AI Safety Red Teamer
$70 - $84 per hourSaidGig
Help strengthen frontier AI systems by uncovering vulnerabilities through rigorous adversarial testing. In this role, you will develop challenging prompts, expose model weaknesses, and assess AI behavior in complex, high-risk, and ambiguous areas. Key Responsibilities
- Design adversarial prompts to stress-test frontier AI models.
- Identify jailbreaks, unsafe behavior, hallucinations, and policy failures.
- Evaluate model robustness across misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive domains.
- Document vulnerabilities and contribute to safety benchmarks and red-teaming reports.
- Collaborate with AI researchers to improve model alignment, robustness, and safety.
- Bachelor''s degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline.
- 5+ years of professional experience in AI safety, AI red teaming, trust and safety, cybersecurity, investigative journalism, life sciences, or a related field.
- Strong analytical reasoning, prompt design, and written communication skills.
- Experience designing adversarial prompts or evaluating frontier AI systems.
- Experience with AI red teaming, RLHF, SFT, AI alignment, or trust and safety.
- Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methods.
- Expertise in one or more ambiguous or high-risk domains, including cybersecurity, biosecurity, political content, misinformation, or scientific safety.
- Remote hourly engagement.
- $70 to $84 per hour.
- Contribute to securing the next generation of frontier AI models alongside AI researchers and safety teams.
- Help shape how AI systems handle complex, real-world safety challenges.
Vacancy posted 1 day ago
Similar jobs that could be interesting for youBased on the AI Safety Red Teamer in United States vacancy
- Handshake seeks a CBRNE Red Teamer to assess AI models for safety gaps in chemical, biological, radiological, nuclear, and explosive domains. You will craft adversarial scenarios, evaluate model refusals, and document failures within a rigorous evaluation framework. The...Suggested
$70 - $84 per hour
...AI Safety Red Teamer is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the...SuggestedRemote jobFor contractors10 hours per week- Mercor is seeking an AI Safety Expert to remotely assess and fortify AI systems. You will red-team conversational models, identify jailbreaks and biases, and generate actionable data to help customers mitigate risks. Strong English and Swedish communication is essential...SuggestedRemote jobContract workFlexible hours
$48 - $62 per hour
...Role Overview Work as a red team human-data expert probing conversational AI models and agents to find vulnerabilities before they reach production. The role focuses on adversarial testing, generating reproducible attack cases and datasets, and documenting failures so...SuggestedHourly payRemote workFlexible hoursSaidGig
United States4 days ago$24 - $35 per hour
...Role Overview Join a red team committed to finding real-world vulnerabilities in conversational AI. You will probe models and agents with adversarial inputs, document reproducible failures, and generate high-quality human data that helps make AI systems safer for customers...SuggestedHourly payRemote workShift workSaidGig
United States5 days ago$17 - $25 per hour
...Role Overview Join a red team that probes conversational AI with adversarial inputs to find vulnerabilities before they reach customers. This text-based role focuses on testing models for bias, misinformation, harmful behaviors, jailbreaks, and prompt-injection style...Hourly payRemote workSaidGig
United States3 days ago$250k - $400k
You'll manage our growing red-team, own delivery for frontier lab customers, and build... ...frontier lab researchers and expert red teamers. We're an early-stage startup, so you should... .... About us Our mission is to automate AI safety , to pave the way for a future where the...Remote workVisa sponsorshipShift work$200k - $400k
...evaluation pipeline for our prompt injection red-teaming line: what we test, how we test... .... About us Our mission is to automate AI safety , to pave the way for a future where the... ...bar. Review tasks, transcripts, and red-teamer submissions, and decide what ships to frontier...Remote workVisa sponsorshipShift work- ...Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who... ...surprises in production Mercor customers trust the safety of their AI because you’ve already probed it...Remote work
Mercor Inc
New York, NY15 hours ago $182k - $238k
...monitoring research agenda attempts to translate compute into safety at scale. Red-teaming previously sat inside the RS (Control) role as a... ...a recurring need, it now needs a dedicated owner. As the AI Red Team Engineer, you will help build the practice of red-teaming...Full timeWork at officeWork from homeVisa sponsorshipRelocation packageFlexible hoursApollo Research
San Francisco, CA4 days ago- ...institutions. In 2025, we started Handshake AI and built the fastest-growing AI data... ...largest scale. About the Role As a CBRNE Red Teamer, you will evaluate whether AI models... ...models for dangerous knowledge gaps in their safety guardrails, testing whether they can be manipulated...Immediate start
$121.6k - $272k
Discover a career that energizes and excites you every day. @2026 TikTok Global Operations AI Content Red Team Analyst - Trust and Safety Location: Employment Type: Regular Job Code: A163404 Share this listing: Responsibilities The Trust & Safety (T&S) GenAI &...Temporary workLocal areaShift work$48 - $62 per hour
...Help strengthen conversational AI systems by probing them with adversarial inputs, identifying vulnerabilities, and producing practical safety data. This remote role focuses on text-based AI red teaming in both English and Danish. Key Responsibilities Test conversational...Hourly payRemote workSaidGig
United Statesa month ago- ...Help strengthen conversational AI systems by probing them with adversarial inputs, identifying... ..., and creating high-quality safety data. This text-based role focuses on finding... ...and attack cases. Key Responsibilities Red team conversational AI models and agents using...Hourly payRemote work
SaidGig
United Statesa month ago $17 - $25 per hour
...Help strengthen conversational AI by testing it from an adversarial perspective. In this... ...agents for weaknesses, create actionable safety data, and help identify risks before they... ...Indonesian is required. Prior experience in AI red teaming, adversarial AI work,...Hourly payRemote workSaidGig
United Statesa month ago- Mercor is building a remote red team for AI safety. You will lead adversarial testing of conversational AI models, focusing on jailbreaks, prompt injections, misuse, and bias exploitation. You will generate high-quality human data, annotate failures, classify vulnerabilities...Remote job
$54 - $111 per hour
A leading AI consultancy is seeking an AI Red-Teamer for adversarial AI testing. This remote role involves conducting advanced testing, generating critical reports, and identifying vulnerabilities in AI models. Ideal candidates will have prior experience in testing and...Remote jobHourly pay10 hours per weekFlexible hours- A technology firm is seeking an AI Red-Teamer for adversarial AI testing. The ideal candidate will be fluent in English and Chinese (Mandarin) and have prior experience in red teaming, cybersecurity, or adversarial testing. The role involves red teaming conversational AI...Remote jobHourly payContract work
- Mercor is seeking a remote red-team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate high-quality data... ...document results and collaborate across projects for robust safety testing. This role focuses on reproducible artifacts,...Remote job
- Mercor seeks a remote AI red-teaming specialist fluent in English and Portuguese to assess safety of conversational models. You will simulate jailbreaks, prompt injections, and misuse scenarios while documenting results for customers. You will generate high-quality human...Remote job
- Anthropic is seeking a Red Team Engineer to uncover vulnerabilities across our AI product ecosystem. You will simulate adversaries, perform comprehensive adversarial testing, and explore novel abuse vectors in our deployed systems. You will design kill-chain style attacks...Flexible hours
- Mercor is seeking a remote Red Team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate actionable red team data for safer AI systems. You will annotate failures, classify vulnerabilities, and document risks using established taxonomies...Remote job
$26 per hour
...Remote Commitment: 10-40 hours/week Role Responsibilities Red-team conversational AI systems using jailbreaks, prompt injections, misuse cases,... ...sensitive or high-risk scenarios in alignment with defined safety guidelines. Requirements Native-level fluency in both English...Remote jobHourly payContract work- Mercor is building a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data that strengthens safety for customers. This is a text-based, higher-sensitivity project where participation is optional and guided by clear guidelines...Remote job
- A leading AI research firm in New York, NY, is looking for a specialist to oversee the red-teaming and adversarial evaluation pipeline for their models. The ideal candidate... ...field and have a deep understanding of LLM safety and adversarial techniques. A strong software...
- Apple Inc. is seeking a researcher to advance red teaming methods for LLMs and diffusion... ...and to develop mitigations to safely deploy AI features across Apple products. You will... ...build tools, metrics, and datasets to assess safety across the deployment lifecycle, and you...
- Mercor is building a remote AI safety red team to probe conversational models and surface vulnerabilities in high-sensitivity topics. You will annotate failures, classify risks, and generate reproducible reports for customers to act on. Before exposure to content, topics...Remote job
- Mercor is building a remote AI red team to probe and test conversational models for vulnerabilities, bias, and safety gaps. This role emphasizes reproducible data and actionable findings across projects and customers. You bring prior red teaming experience in AI or cybersecurity...Remote job
$26 per hour
A tech consulting firm is seeking a remote contractor to engage in AI red teaming activities. The ideal candidate will work on evaluating conversational AI systems and generating human data through careful documentation and classification of vulnerabilities. Fluency in...Remote jobHourly payFor contractors10 hours per weekFlexible hours- Anthropic’s Safeguards team is seeking a Red Team Engineer to help ensure the safety of our deployed AI systems and products. You will take an adversarial approach to uncover vulnerabilities across our product ecosystem before they can be exploited by malicious actors....
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Red Teamer. Be the first to apply!
Related searches
- wind turbine safety United States
- safety analyst United States
- safety attendant United States
- patient safety assistant United States
- vp safety United States
- safety intern summer United States
- awp safety United States
- safety specialist United States
- construction safety United States
- oilfield safety United States