Radiological Safety Red-Team Expert for AI Risk
Mercor Inc
Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The work centers on writing challenging, domain-specific prompts across benign, dual-use, and adversarial levels, and evaluating model responses against a defined policy standard.
You will document judgments with clear rationales for non-specialists, read and write about misuse scenarios, and contribute reference answers with technical reasoning.
#J-18808-LjbffrVacancy posted 5 days ago
Similar jobs that could be interesting for youBased on the Radiological Safety Red-Team Expert for AI Risk in San Francisco, CA vacancy
$20 - $22 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Experts — English & Odia Type:... ...Role Responsibilities Red team conversational AI models and... ...vulnerabilities, and flag systemic risks. Apply structure using...RiskContract workSummer workRemote workMercor
San Francisco, CA2 days ago$20 - $22 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Experts — English & Punjabi Type:... ...Role Responsibilities Red team conversational AI models and... ...vulnerabilities, and flagging systemic risks. Apply structure by...RiskContract workSummer workRemote workMercor
San Francisco, CA19 days ago- ...OpenAI is seeking a Red Teamer focused on cyber to evaluate model capabilities and safeguards... ..., and translate results into actionable risk assessments for Security, Research,... ...background, with capability to build testing tools and collaborate across teams. #J-18808-Ljbffr...Risk
OpenAI
San Francisco, CA2 days ago - ...Work Model: Onsite Industry: Applied AI / AI research data Compensation: $130K... ...domains. The Opportunity As the AI Safety & Red Teaming Lead, you will do hands-on adversarial... ...model behavior, safety evaluation, and risk priorities. Write precise risk specifications...Risk
TalentPluto, Inc.
San Francisco, CA1 day ago $65 - $75 per hour
...technical talent with leading AI research labs. Headquartered... ...challenging single-turn prompts in radiological safety, labeled as benign, dual-use,... ...with radiological safety experts to assess misuse potential in... ...@mercor.com PS: Our team reviews applications daily. Please...SuggestedContract workSummer workRemote work$90 per hour
...assembling a small panel of nuclear and radiological professionals to audit how AI models respond to sensitive... ..., health physicists and radiation safety officers, radiochemists, and former... ...licensing, inspection, peer review) or AI red teaming is a strong plus. ## Before you...Contract workSuperAnnotate
San Francisco, CA20 days ago$50 - $70 per hour
...assembling a small panel of nuclear and radiological professionals to audit how AI models respond to sensitive... ..., health physicists and radiation safety officers, radiochemists, and former... ...licensing, inspection, peer review) or AI red teaming is a strong plus. Before you...Contract workTemporary workRemote workBraintrust
San Francisco, CA23 days ago- ...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 while answering legitimate questions fully while refusing genuinely...
Mercor Inc
San Francisco, CA5 days ago - ...Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier... ...weaknesses, and assess safety across high-risk topics. Join a cutting-edge research... ...behavior, and contribute to safety benchmarks and red-teaming reports. #J-18808-LjbffrRisk
Mercor Inc
San Francisco, CA13 hours ago - ...mature and scale Penetration Testing and Red Team programs. This hands-on leadership role combines... ...with building the operating model and AI-assisted tooling that accelerates... ...staffing, and metrics, partner with engineering, risk, and audit teams, hire and mentor staff, and...Risk
SoFi
San Francisco, CA2 days ago - ...seeks an Offensive Security Engineer to join the Red Team, conducting end-to-end adversary simulations... ...campaigns, develop tooling, and test detections, while explaining risk to leadership and advising durable fixes with a focus on secure AI-enabled platforms. #J-18808-LjbffrRisk
100 Salesforce, Inc.
San Francisco, CA4 days ago $16 - $22 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Experts — English & Telugu Type:... ...Role Responsibilities Red team conversational AI models and... ...vulnerabilities, and flagging systemic risks. Apply structure by...RiskContract workSummer workRemote work$17 - $25 per hour
...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... ..., and flag systemic risks Apply structure: follow... ...Mercor customers trust the safety of their AI because you’...RiskHourly payContract workRemote workMercor
San Francisco, CA23 days ago- ...Offensive Security Engineer - Red Team The Experience We are looking... ...how attackers could abuse AI-driven systems. You will also... ...Explain attack chains and business risk clearly to executive... ...OSEP), Offensive Security Web Expert (OSWE), Certified Red Team Operator...Risk
Leadout Capital
San Francisco, CA2 days ago $100 per hour
...Careers is hiring chemists and chemical safety professionals to audit how AI models respond to sensitive... ...toxicology, industrial hygiene, chemical risk assessment, regulatory compliance, or... ...~ Prior experience with AI safety, red-team review, model evaluation, content moderation...RiskPermanent employmentFull timeSuperAnnotate
San Francisco, CA20 days ago$70 - $84 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Red Teamer Type: Contract Compensation... ...contribute to safety benchmarking and red-teaming reports. Collaborate with AI researchers...Contract workSummer workRemote work$75 per hour
...technical talent with leading AI research labs. Headquartered... ...single-turn prompts in radiological safety, labeled as benign, dual-use... ...responses. Collaborate with experts to draw reliable lines between... ...material. Preferred Red-teaming experience. Prior technical...Remote jobContract workSummer workMercor
San Francisco, CA11 days ago$60 - $70 per hour
...technical talent with leading AI research labs. Headquartered in... ...Jack Dorsey . Position: AI Safety Practitioner Type: Contract... ...AI researchers and safety teams on ongoing evaluation initiatives... ...Experience reviewing complex, high-risk, or ambiguous content....RiskContract workSummer workRemote workMercor
San Francisco, CA18 days ago$117.2k - $223.9k
...SalesforceSalesforce is the #1 AI CRM, where humans with... ...Security Engineer - Red TeamThe ExperienceWe are... ...to join our Red Team, which simulates real attackers... ...attack chains and business risk clearly to executive... ...Offensive Security Web Expert (OSWE), Certified Red Team...RiskFull timeSalesforce
San Francisco, CA5 days ago$200k - $240k
...Senior Application Security Engineer (Red Team) San Francsico, CA About Altruist... ...wealth management industry by building an AI platform for wealth professionals. We partner... ...authorization and exploitability assessments on high-risk attack paths Conduct cloud pentests and...RiskWork at officeImmediate start3 days per weekAltruist
San Francisco, CA4 days ago$80 - $150 per hour
...technical talent with leading AI research labs.... ...Health Clinical Advisor (AI Safety Benchmark Project) Type... ...and provide expert judgment to calibrate automated... ...domains, including suicide risk, therapeutic guidance, and... ...clinical teams. Application Process...RiskContract workTraineeshipSummer workRemote work$65 - $75 per hour
...technical talent with leading AI research labs.... ...Position: Radiologicals Safety for Redteaming Type... ...-turn prompts in the radiological safety domain, labeled... .... Collaborate with experts to ensure models... ...rationales. Preferred ~ Red-teaming experience in...Contract workSummer workRemote work$174k - $252k
...Research Engineer, Frontier Safety Mitigations, DeepMind... ...About the job Our team focuses on de-risking model launches by... ..., Biological, Radiological, Nuclear, Conventional... ...building novel evaluations, red-teaming, researching... ...seriously as AI advances. Because of...RiskGoogle LLC
San Francisco, CA13 hours ago- ...Leadout Capital is seeking an Offensive Security Engineer to join the Red Team, responsible for end-to-end adversary simulations across... ...engineers, coordinate with cross-functional teams, and communicate risk to executives while adhering to OPSEC and engagement rules. #J-1...Risk
Leadout Capital
San Francisco, CA14 hours ago - ...frameworks, runtimes, and rendering surfaces, including AI/agent-driven experiences. You will own risk management for guest-user data access, implement least... ..., and shape secure-by-default patterns across multi‑team programs, working with senior engineering teams. #J-...Risk
Jobleads-US
San Francisco, CA2 days ago - ...Mercor is seeking AI Safety Experts fluent in English and Urdu for a remote contract role. You will red team conversational AI models, identify vulnerabilities, and generate actionable... ...with reproducible data, and communicate risks to both technical and non-technical...RiskContract workRemote work
Mercor Inc
San Francisco, CA3 days ago $268k - $384k
...talent-dense, high-agency AI safety team at Lila that will... ...identify and mitigate risks from scientific superintelligence... ...input with the expert-program team, and... ...capabilities, interpret red-team findings and evaluate... ...proliferation, radiological misuse, weapons-related...RiskFull timeWork at officeLocal areaImmediate startFlexible hours- ...seeking a Technical Program Manager for AI Safety & Safeguards in San Francisco, hybrid 3 days... ..., product managers, and legal and policy teams to translate safety priorities into... ...actionable plans, align technical decisions with risk management, and deliver durable...RiskWork at office
Openai
San Francisco, CA3 days ago $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$220k - $300k
...About OpenAI Foundation AI is already changing how... .... About the team AI Resilience helps society... ...across biosecurity, model safety, cybersecurity, children... ...them independently, red-teaming them, researching... ...frontier AI capabilities and risks closely enough to have...RiskOpenAI Foundation
San Francisco, CA4 days ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Radiological Safety Red-Team Expert for AI Risk. Be the first to apply!
Related searches
- subject matter expert San Francisco, CA
- technology expert San Francisco, CA
- fulfillment expert San Francisco, CA
- guest service support expert San Francisco, CA
- risk adjustment San Francisco, CA
- geopolitical risk San Francisco, CA
- risk underwriter San Francisco, CA
- risk intern San Francisco, CA
- at risk youth San Francisco, CA
- technology risk San Francisco, CA