Remote AI Safety Red Teamer for Frontier Models
Mercor
San Francisco, CA
- Remote job
Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk topics. Responsibilities include stress-testing frontier models, identifying jailbreaks and policy failures, and collaborating with researchers to improve alignment and safety. #J-18808-Ljbffr Mercor
Vacancy posted 2 days ago
Similar jobs that could be interesting for youBased on the Remote AI Safety Red Teamer for Frontier Models in San Francisco, CA vacancy
- Mercor is seeking an AI Safety Red Teamer on a remote, contract basis. You will design adversarial prompts to stress-test frontier AI models and identify jailbreaks, unsafe behaviors, hallucinations, and policy failures. You will evaluate model robustness across domains...Remote jobContract work
- Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design prompts, uncover model weaknesses, and assess safety across high-risk topics. Join a cutting-edge research environment,...Suggested
$100k - $120k
...Labs: 10a Labs is the safety and threat-intelligence layer trusted by frontier AI labs, AI unicorns, Fortune... .... Our adversarial red teaming, model evaluations, and intelligence... ...are seeking an AI Red Teamer with deep... ...Work Environment: Fully remote, U.S.-based Health...Remote workFull timeWork at office2 days per week$70 - $84 per hour
...technical talent with leading AI research labs.... ...Dorsey . Position: AI Safety Red Teamer Type: Contract Compensation... ...0–$84/hour Location: Remote Role Responsibilities... ...adversarial prompts to stress-test frontier AI models . Identify jailbreaks,...Remote workContract workSummer work$17 - $25 per hour
...technical talent with leading AI research labs. Headquartered in... ...Jack Dorsey . Position: AI Safety Experts — English & Vietnamese... ...$17–$25/hour Location: Remote Role Responsibilities Red team conversational AI models and agents by conducting jailbreaks...Remote workContract workSummer workMercor
New York, NY16 days ago- ...Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing, prompt design, and rigorous model evaluation. You will simulate jailbreaks, assess unsafe behaviours, and document weaknesses to inform...
- ...We are seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk, and ambiguous ("grey-area...
$70 - $84 per hour
...About the role AI Safety Red Teamer is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack... ...gap. Adversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers...Remote workContract workFor contractors10 hours per weekAuraOne
San Jose, CA21 days ago$250k - $400k
...About Trajectory Safety data needs to... .... As AI advances, we build... ...of focus include red teaming, control... ...most powerful AI models. You'll work alongside... ...engineers and red teamers, building tools... ...the safety of frontier AI systems. Agent... ...We are open to remote for the right...Remote workRelocationVisa sponsorshipShift workTrajectory Labs
Berkeley, CA2 days ago$66.56k - $197.6k
...AI Red Teamer (LLM Generalist) Location: Remote (USA) Employment type: W-2, hourly, employed... ...stress-test large language models by intentionally trying... ...directly supports AI safety and model robustness for... ...responsible development of frontier AI systems....Remote workHourly payFull time- ...Frontier Model Misuse Red Team Specialist is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure... ...with the rubric clause it violated so the safety team can patch the gap. Why this role...Remote jobHourly payFor contractors10 hours per week
- Mercor is assembling a panel of chemistry and chemical safety experts to red-team frontier AI models. The goal is to test whether a model can correctly... ...misuse potential of chemical threats in AI systems. This remote, full-time role offers paid training through a two-week...Remote jobFull time
$120k - $150k
...description This is a remote US position. Candidates... ...The Role As a Senior Red Team Engineer, you will... ...What You´ll Bring ~ AI-Driven Penetration Testing: Apply frontier AI models to enhance penetration testing... .... OffSec AI Red Teamer (OSAI / AI-300) – Preferred...Remote workFull timeFlexible hours$22 per hour
...and technical talent with leading AI research labs. Headquartered in... ...Jack Dorsey . Position: AI Safety Experts — English & Malayalam... ...Compensation: $20–$22/hour Location: Remote Responsibilities Red team conversational AI models and agents. Perform jailbreaks,...Remote workContract workSummer workMercor Inc
United States2 days ago- A technology firm is seeking an AI Red-Teamer for adversarial AI testing. The ideal candidate... ...involves red teaming conversational AI models, generating human data, and identifying... ...risks to diverse stakeholders. This is a remote hourly contract role offering competitive...Remote jobHourly payContract work
$100 per hour
...hiring a part-time , fully remote AI Engineer to focus on post-training... ...alignment for large language models at scale. The work centers on supervised fine-tuning and safety-focused evaluation, with hands... ...adversarial test suites, red-team integration (for example,...Remote workHourly payPart timeWork at officeDataJobs
Newport, RI2 days ago- AuraOne is seeking a Bilingual Czech STEM Expert (PhD) for a remote role in AI safety focused on red-teaming efforts. The role involves crafting adversarial... ...and thoroughly documenting findings to enhance overall model robustness. Successful candidates will have substantial...Remote job
- SaidGig is seeking a text-based, remote, hourly role to strengthen conversational AI systems. You will probe models with adversarial inputs,... ...vulnerabilities, and build high-quality safety datasets, reports, and attack... .... Responsibilities include red-teaming AI models, reviewing...Remote jobHourly pay
- 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
$150 per hour
...real engineering tasks, analyze the model outputs, and document failures to... ...agents. You will vibe-code with frontier models, identify bugs, explain failures, and red‑team them to uncover unsafe or... ...before real users see them. Flexible, remote work; compensation up to $150+...Remote jobHourly payFlexible hours$246k
...with the world’s most advanced AI-native platform. We work on... ...Lab. This role brings together frontier AI research, deep... ...anticipating what advances in models and agentic systems could make... ...researchers, incident responders, red teamers, and other security experts to...Remote workPermanent employmentWork experience placementWork at officeLocal areaRemote8 days ago- ...strengthen conversational AI systems by probing them with... ...and creating high-quality safety data. This text-based role... ...cases. Key Responsibilities Red team conversational AI models and agents using jailbreaks... ..., or writing. Work Terms Remote, hourly position. All work...Remote workHourly pay
- Mercor is seeking a remote AI red team specialist to probe and improve safety of conversational models. You will perform adversarial testing, annotate failures, and generate data to surface vulnerabilities and risks for customers. This role emphasizes structured methodologies...Remote job
- Mercor is seeking AI Safety Experts to work remotely. Fluency in English and Swedish, plus experience in AI adversarial testing, are essential for this contract role. You will red-team conversational AI models, identify jailbreaks, bias exploitation, and generate actionable...Remote jobContract work
- 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
$17 - $25 per hour
...technical talent with leading AI research labs. Headquartered in... ...Jack Dorsey . Position: AI Safety Experts — English & Indonesian... ...$17–$25/hour Location: Remote Role Responsibilities Red team conversational AI models and agents. Focus on jailbreaks...Remote workContract workSummer workMercor
San Francisco, CA15 days ago- AuraOne is seeking a Biology Expert (PhD) for its remote AI Safety red-team track. You design adversarial prompts to probe known weaknesses,... ..., and tie it to policy clauses for patching. You will score model defenses across turns, triage new attack vectors, and maintain...Remote jobContract work10 hours per week
- ...physics expert to help evaluate frontier AI systems by distinguishing legitimate radiological safety questions from those with misuse potential. The role is remote and per-task, requiring hands-on... ...sound responses. You will evaluate model outputs, draft comprehensive reference...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
- Google DeepMind’s CBRNE team seeks a Threat Modeller SME to build and advance threat models for dual-use risks in advanced AI systems. You will work closely with the... ...-paced environment. You will contribute to frontier safety with real-world threat intelligence. #J-18...
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Remote AI Safety Red Teamer for Frontier Models. Be the first to apply!
Related searches
- software engineering manager remote San Francisco, CA
- remote recruitment consultant San Francisco, CA
- remote data manager San Francisco, CA
- senior php developer remote San Francisco, CA
- benefits specialist remote San Francisco, CA
- remote video game San Francisco, CA
- remote typing work San Francisco, CA
- remote fashion San Francisco, CA
- remote autocad jobs San Francisco, CA
- remote operation drilling engineer San Francisco, CA