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 2 days ago
Similar jobs that could be interesting for youBased on the AI Safety Red Teamer in United States vacancy
$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- AI Trainer Jobs is seeking a Bilingual Korean STEM Expert (PhD) for a remote AI Safety red-team track. You will craft adversarial prompts, document failures with rigor, and map each jailbreak to the violated rubric to help patch gaps. Reviewers simulate attacks, assess...SuggestedRemote jobFor contractors
- AuraOne is seeking a Bilingual German Generalist Expert — AI Safety for a remote red-team track that stress-tests AI systems against adversarial prompts. Reviewers craft attack scenarios, document failures, and pair each jailbreak with the violated rubric clause so the...SuggestedRemote job
$70 - $84 per hour
...Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors... ..., Larry Summers , and Jack Dorsey . Position: AI Safety Red Teamer Type: Contract Compensation: $70–$84/hour Location...SuggestedContract workSummer workRemote work- AI Trainer Jobs is seeking a Bilingual Thai STEM Expert (PhD) for a remote AI safety red-team role. Reviewers craft attack scenarios, document failures, and map breaches to rubric clauses to guide patching. This contractor position emphasizes adversarial evaluation, policy...SuggestedFor contractorsRemote work
$68 - $72 per hour
AI Trainer Jobs is seeking a bilingual Japanese STEM expert (PhD) for a remote AI Safety red-team role. You will design jailbreak prompts, document failures, and patch gaps to harden AI systems before deployment. Responsibilities include crafting adversarial scenarios,...Remote jobHourly payFor contractors$16 - $22 per hour
...Help make conversational AI safer by probing models with adversarial inputs, identifying vulnerabilities, and producing actionable red-team data. This text-based remote role focuses on testing AI behavior across sensitive areas, including bias, misinformation, and harmful...Hourly payRemote workSaidGig
United States1 day ago$20 - $22 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...Summers , and Jack Dorsey . Position: AI Safety Experts — English & Bengali Type: Contract... ...: Remote Role Responsibilities Red team conversational AI models and agents...Contract workSummer workRemote work$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...Hourly payRemote workFlexible hoursSaidGig
United States1 day 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 States1 day ago$16 - $22 per hour
...Role Overview Help make conversational AI systems safer by testing them with adversarial... ..., and creating high-quality red-team data. This text-based remote role involves... ...completeness, appropriateness, and potential safety issues. Annotate failures, classify vulnerabilities...Hourly payRemote workSaidGig
United States1 day ago$48 - $62 per hour
...Probe conversational AI systems for weaknesses before they reach users. In this remote... ...uncover vulnerabilities, create high-quality safety data, and produce practical findings that... ...are provided. Key Responsibilities Red team conversational AI models and agents through...Hourly payRemote workSaidGig
United Statesmore than 2 months 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 Statesmore than 2 months ago$151.2k - $189k
Scale's Red Team and Safety function stress-tests the most capable AI models in the world, and shapes how labs, governments, and enterprises deploy them. We are hiring a Technical Program Manager to own day-to-day partnerships with frontier model developers. This is a hands...Full timeScale AI
New York, NY2 days ago$16 - $22 per hour
...Help strengthen conversational AI by probing models for weaknesses, documenting risks, and producing high-quality safety data. This text-based remote role focuses on adversarial testing and review of AI outputs, including work involving sensitive subjects such as bias,...Hourly payRemote workSaidGig
United States3 days ago- ...TLDR: We're looking for an AI Red Team Engineer to break LLM-powered systems responsibly, automate the repetitive attacks, and turn their... ...it, and write it up. About us White Circle is an AI Safety company building the safety, reliability, and optimization layer...Local area
Visa Hunt
Eastern, KY3 days ago $25 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...Summers , and Jack Dorsey . Position: AI Safety Experts — English & Indonesian Type:... ...Location: Remote Role Responsibilities Red team conversational AI models and agents...Contract workSummer workRemote workMercor
San Francisco, CA8 days ago$48 - $62 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...Larry Summers, and Jack Dorsey. Position: AI Safety Experts — English & Danish Type:Contract Compensation... ...Location:Remote Role Responsibilities Red team conversational AI models and agents...Contract workSummer workRemote work- ...Role Overview Help assess frontier AI systems at the boundary between legitimate radiological safety work and potentially dangerous misuse. You will apply practitioner... ...reporting across multiple authorized users. Red-teaming experience is preferred. Technical writing...For contractorsRemote work
SaidGig
United States23 days ago - Mercor is assembling a red team for AI safety. You will review model outputs, simulate adversarial inputs, and surface vulnerabilities across prompts and conversations. You will generate high-quality human data, annotate failures, classify risks, and produce reproducible...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
- AuraOne is seeking a Bilingual Korean Generalist Expert — AI Safety for a remote red-team track that stress-tests AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and map each successful jailbreak to the violated rubric...Remote work
- AuraOne is seeking a Bilingual Dutch (Belgium) STEM Expert (PhD) to work remotely as a contractor on AI Safety red-teaming. You will craft adversarial prompts, document failures, and pair each jailbreak with the violated rubric clause so the safety team can patch gaps....Remote jobHourly payFor contractors
- AuraOne is seeking a bilingual Indonesian STEM expert (PhD) for a remote AI safety red-team role that stress-tests AI systems against adversarial prompts. Reviewers craft attack scenarios, document failures, and pair each successful jailbreak with the rubric clause it violated...Remote job
- 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
- AuraOne is seeking a Bilingual Vietnamese STEM Expert (PhD) for an AI Safety remote red-team role. You will design adversarial prompts to test AI systems, document failures with rigorous reproduction steps, and pair each jailbreak with the clause it violated so the safety...Remote jobFor contractors
- AuraOne is seeking a Biology Expert (PhD) for its remote AI Safety red-team track. You design adversarial prompts to probe known weaknesses, document each failure with reproduction steps, and tie it to policy clauses for patching. You will score model defenses across turns...Remote jobContract work10 hours per week
- AuraOne is seeking a Bilingual Chinese STEM Expert (PhD) for AI Safety, a remote red-team track that stresses testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and pair each successful jailbreak with the violated rubric...For contractorsRemote work
- Mercor is assembling a panel of chemistry and chemical safety experts to red-team frontier AI models and assess misuse potential of technical requests. You will write challenging prompts across benign, dual-use, and adversarial levels, evaluate model responses, and craft...
- Obsidian is looking for data experts to join a red team that probes AI models with adversarial inputs. This role requires fluency in both English... ...AI and cybersecurity, emphasizing the importance of AI safety. Work will be structured, with clear guidelines and wellness...Remote job
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Red Teamer. Be the first to apply!
Related searches
- senior safety specialist United States
- warehouse safety United States
- patient safety assistant United States
- safety physician United States
- director of quality & patient safety United States
- safety technician United States
- safety sales United States
- traffic safety United States
- aviation safety assistant office automation United States
- product safety specialist United States