Frontier AI Safety Red Team Expert
Jobleads-US
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 safety benchmarks and red-teaming reports, collaborating with researchers to improve alignment and robustness.
This role requires strong analytical writing and a track record in cybersecurity, safety, or life sciences, with at
#J-18808-Ljbffr Jobleads-USVacancy posted 2 days ago
Similar jobs that could be interesting for youBased on the Frontier AI Safety Red Team Expert in New York, NY vacancy
$48 - $62 per hour
Probe conversational AI systems for weaknesses before they reach users. In this remote... ...vulnerabilities, create high-quality safety data, and produce practical findings that... ...resources are provided. Key Responsibilities Red team conversational AI models and agents...SuggestedHourly payRemote work- ...remote adversarial testing specialist to probe conversational AI systems for weaknesses. You will perform red team exercises, annotate findings, and create reproducible attack data to help strengthen AI safety. The role requires fluent English and Swedish, experience in...SuggestedRemote jobHourly pay
- ...remote, hourly role to strengthen conversational AI systems. You will probe models with... ...identify vulnerabilities, and build high-quality safety datasets, reports, and attack cases. Responsibilities include red-teaming AI models, reviewing outputs on bias and safety...SuggestedRemote jobHourly pay
$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 & Odia Type: Contract Compensation... .../hour Location: Remote Responsibilities Red team conversational AI models and agents to...SuggestedContract workSummer workRemote work- 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 prompts to test AI system weaknesses and thoroughly documenting findings to enhance overall model robustness. Successful...SuggestedRemote job
$20 - $22 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Experts — English & Punjabi Type: Contract... ...: Remote Role Responsibilities Red team conversational AI models and agents. Focus...Contract workSummer workRemote workMercor
New York, NY13 days ago$48 - $62 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Experts — English & Swedish Type: Contract... ...: Remote Role Responsibilities Red team conversational AI models and agents to...Contract workSummer workRemote workMercor
New York, NY7 days ago- ...We are seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts... ...and contribute to safety benchmarking and red-teaming reports. Collaborate with AI researchers to...
$16 - $22 per hour
Help identify weaknesses in conversational AI by testing model responses, uncovering risks, and creating actionable safety data in both English and Tamil. Role Overview This... ...reports, datasets, and attack cases that teams can use to strengthen AI systems. Qualifications...Hourly payRemote work- AuraOne is seeking a Bilingual German STEM Expert (PhD) for a remote AI Safety role focused on adversarial evaluation. You will design prompts, document failures with reproducible steps, and score defenses across conversations to harden models before release. Work as a...Remote jobFor contractorsFlexible hours
$70 - $84 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Red Teamer Type: Contract... ...prompts to stress-test frontier AI models . Identify jailbreaks... ...safety benchmarking and red-teaming reports. Collaborate with...Contract workSummer workRemote work- ...ActiveFence) is a leading trust, safety, and security company.... ...the emerging world of AI and focus on... ...the world's premier CBRN experts—high-stakes, project-based... ...to help us secure the frontier. The invitation is... ...moderation, academic review, red‑teaming, or consulting...FreelanceRemote work
- ...Mercor, we believe the safest AI is the one that’s already... ...us. We are assembling a red team for this project - human data experts who probe AI models with... ...customers trust the safety of their AI because you’ve... ...driven AI red teaming at the frontier of safety Play a direct...Remote work
$65 - $75 per unit
...Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors... ...Dorsey . Position: Nuclear Engineering & Safeguards Experts for Red Team Type: Contract Compensation: $65–$75 per task Location...Contract workSummer workRemote workFlexible hours$65 - $70 per hour
...Compensation: $65-$70 per hour Join an advanced AI safety initiative focused on improving how next... ...evaluate AI-generated content, develop expert-level prompts, and help ensure AI models... ...reviewing, evaluating, grading, or red-teaming scientific or technical content. Strong...Hourly payWeekly payContract workPart timeFor contractorsH1bImmediate startRemote workVisa sponsorshipFlexible hoursWeekday work$65 - $75 per unit
...technical talent with leading AI research labs. Headquartered in... ...-turn prompts in radiological safety, labeled as benign, dual-use,... ...Collaborate with radiological safety experts to assess misuse potential in... ...****@*****.*** PS: Our team reviews applications daily....Contract workSummer workRemote work$50 - $70 per hour
...radiological professionals to audit how AI models respond to sensitive questions in... ...national labs), health physicists and radiation safety officers, radiochemists, and former... ...licensing, inspection, peer review) or AI red teaming is a strong plus. Before you apply This role...Remote jobTemporary work$174k - $252k
...of Google’s nuclear safety policy. Communicate... ...shielding defeat, and RDD/RED mechanics.Preferred... ....Experience in AI safety, evaluations, red-teaming, or applied AI research... ...Subject Matter Expert (SME) in the CBRNE team... ...mitigating safety risks of frontier AI models (primarily...Google
New York, NY4 days ago- Mercor is seeking a Chemistry Expert (PhD) for remote, contract-based engagement in AI safety. You will write expert-level prompts on chemistry, evaluate model responses... ...and conversations. Collaborate with AI research teams, work independently and asynchronously to meet...Remote jobContract workImmediate start
- Veeva Systems seeks a Senior Safety Domain Expert for Veeva Falcon to bridge hands-on case processing... ...will collaborate with internal technical teams and early adopters, acting as the Voice... ...expedited reporting, and experience with AI-driven tools to enhance PV operations....Remote job
$16 - $22 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Experts — English & Gujarati Type: Contract... ...: Remote Role Responsibilities Red team conversational AI models and agents to...Contract workSummer workRemote work- About the work Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely...
- Physics Experts (PhD Or Master's), Are You There? Athyna is building... ...to work directly on frontier AI post-training with leading AI... ...model performance, conduct red-teaming exercises, and help refine AI... ...created by the Center for AI Safety and Scale AI. Engagement options...Full timePart timeRemote workFlexible hours
$37 per unit
...technical talent with leading AI research labs.... ...Dorsey . Position: AI Safety Specialist Type: Contract... ...to AI research teams to improve training data... ...Collaborate with subject matter experts to ensure consistency,... ...in AI safety , red teaming ,...Contract workSummer workRemote work$60 - $70 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...Summers , and Jack Dorsey . Position: AI Safety Practitioner Type: Contract Compensation... ...with AI researchers and safety teams on ongoing evaluation initiatives. Qualifications...Contract workSummer workRemote workMercor
New York, NY16 days ago- TELUS Digital is seeking psychology professionals to help evaluate AI-generated content for safety, helpfulness, and responsibility. You will work remotely as an independent contractor, contributing to a global AI community. You’ll review flagged content, analyze AI interactions...Remote jobFor contractorsFlexible hours
- ...fixed working days Weekday is an AI-native recruiting platform. We... ..., and we're looking for legal experts to build and judge the tasks... ...so the model (and the team) learns from them Working across... ...role A front-row seat to how frontier AI models are trained and evaluated...Full timeContract workRemote workFlexible hoursWeekday work
$120 per hour
Medical Expert, German (Germany) is a remote clinical-review... ...track for evaluating AI outputs that touch... ...adherence; flag patient-safety issues; and document the... ...reasoning so the modeling team can close the gap. Why this... ...reasoning, dosing, and red-flag handling on a structured...For contractorsRemote work10 hours per week$70 per hour
...chemists to help make advanced AI models safer. You'll apply... ...workflow.What you'll doWrite expert-level prompts across specialized... ...Sound judgment around chemical safety and the responsible handling of... ...Experience reviewing, grading, or red-teaming technical content.Project...Remote jobPart time- AuraOne is seeking a Medical Expert (German, Germany) for remote Clinical AI Review. You will assess AI-generated medical outputs against German clinical... ...differential diagnosis and dosing reasoning, and flag safety issues when needed. Ideal candidates hold an active medical...Remote jobFor contractors10 hours per week
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Frontier AI Safety Red Team Expert. Be the first to apply!
Related searches
- subject matter expert New York, NY
- technology expert New York, NY
- fulfillment expert New York, NY
- guest service support expert New York, NY
- sql expert New York, NY
- radiation safety New York, NY
- safety physician New York, NY
- entry level safety New York, NY
- safety valve technician New York, NY
- safety attendant New York, NY