AI Safety Expert - Adversarial ML
$16 - $22 per hourMercor
Job Description
Job Description
About the job
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey .
Position: AI Safety Experts — English & Urdu
Type: Contract
Compensation: $16–$22/hour
Location: Remote
Role Responsibilities
- Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
- Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
- Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
- Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
- Work independently and asynchronously to meet deadlines while improving AI model performance .
Qualifications
Must-Have
- Native fluency in English and Urdu .
- Strong judgment about language and content accuracy.
- Rigorous attention to detail and ability to notice subtle errors.
- Ability to work to guidelines and quality standards consistently.
- Strong communication skills for both technical and non-technical audiences.
- Adaptability to move across projects, task types, and customers.
Preferred
- Experience in Adversarial ML : jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Background in Cybersecurity : penetration testing, exploit development, reverse engineering.
- Knowledge of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.
Application Process (Takes 20–30 mins to complete)
- Upload resume
- AI interview based on your resume
- Submit form
Resources & Support
- For details about the interview process and platform information, please check:
- For any help or support, reach out to: View email address on ziprecruiter.com
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.
Vacancy posted 3 days ago
Similar jobs that could be interesting for youBased on the AI Safety Expert - Adversarial ML in San Francisco, CA vacancy
$16 - $22 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Experts — English & Bengali Type: Contract... .... Preferred Experience in Adversarial ML : jailbreak datasets, prompt injection...SuggestedContract workSummer workRemote workFlexible hoursMercor
San Francisco, CA4 days ago$17 - $25 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Experts — English & Indonesian... ...red teaming experience in AI adversarial work , cybersecurity , or... ...Experience in Adversarial ML , Cybersecurity , and socio...SuggestedContract workSummer workRemote workMercor
San Francisco, CA9 days ago$20 - $22 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Experts — English & Punjabi Type:... ...in red teaming, AI adversarial work, cybersecurity, or socio... ...Experience with Adversarial ML , Cybersecurity , or Socio...SuggestedContract workSummer workRemote workMercor
San Francisco, CA4 days ago$24 - $35 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Experts — English & Thai Type:... ...red teaming experience in AI adversarial work , cybersecurity , or... ...Experience in Adversarial ML , Cybersecurity , or socio...SuggestedFull timeContract workSummer workRemote work- ...Mercor, we believe the safest AI is the one that’s already... ...this project - human data experts who probe AI models with adversarial inputs, surface... ...Specialties Adversarial ML: jailbreak datasets, prompt... ...Mercor customers trust the safety of their AI because you’ve...SuggestedPart timeRemote work
Mercor
San Francisco, CA15 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... ...Remote Role Responsibilities Design adversarial prompts to stress-test frontier AI...Contract workSummer workRemote workMercor
San Francisco, CA7 days ago$65 - $75 per unit
...technical talent with leading AI research labs. Headquartered in... .... Position: Radiologicals Safety for Redteaming Type:... ...labeled as benign, dual-use, and adversarial. Evaluate model responses against... .... Collaborate with experts to ensure models correctly judge...Contract workSummer workRemote workMercor
San Francisco, CA18 days ago$145 per hour
...connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors... ...Angelo , Larry Summers , and Jack Dorsey . Position: ML Research PhD Experts (ICML / NeurIPS / ICLR Publications) Type: Contract...Remote jobContract workSummer workMercor
San Francisco, CA9 days ago$60 - $70 per hour
...Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors... ...Angelo , Larry Summers , and Jack Dorsey . Position: AI Safety Practitioner Type: Contract Compensation: $60–$70/hour...Contract workSummer workRemote workMercor
San Francisco, CA1 day ago$293.5k
General Information Job Title Expert Senior Manager, AI Engineering Job ID 104335 Work Areas... ...improvementBalance performance, safety, responsible AI principles, and cost across... ...):8-12+ years in software engineering, ML engineering, or applied AI roles with significant...Permanent employmentFull timeApprenticeshipWork at officeLocal areaWork from homeHome office3 days per weekBain & Company
San Francisco, CA1 day ago$100 per hour
...Description SME Careers is hiring chemists and chemical safety professionals to audit how AI models respond to sensitive questions in the field.... ...gave to it. You classify the request (benign, dual-use or adversarial), mark each answer as safe or unsafe and say why, rank...Permanent employmentFull timeSuperAnnotate
San Francisco, CA12 days ago$50 - $70 per hour
...radiological professionals to audit how AI models respond to sensitive questions in... ...classify the request (benign, dual-use or adversarial), mark each answer as safe or unsafe and... ...national labs), health physicists and radiation safety officers, radiochemists, and former...Contract workTemporary workRemote workBraintrust
San Francisco, CA15 days ago$90 per hour
...radiological professionals to audit how AI models respond to sensitive questions in... ...classify the request (benign, dual-use or adversarial), mark each answer as safe or unsafe and... ...national labs), health physicists and radiation safety officers, radiochemists, and former...Contract workSuperAnnotate
San Francisco, CA12 days ago$75 per hour
...and technical talent with leading AI research labs. Headquartered in San... ...-turn prompts in radiological safety, labeled as benign, dual-use, and adversarial. Evaluate AI model responses against... ...responses. Collaborate with experts to draw reliable lines between routine...Remote jobContract workSummer workMercor
San Francisco, CA3 days ago- ...Compensation Range: $243,000 - $249,000Created: 2026-10-13Apply: will play a senior leadership role in shaping and delivering agentic AI and machine learning solutions for defense clients across the public and private sector.Who you'll work withDriving lasting impact...ApprenticeshipFor subcontractorEasy work
McKinsey & Company
San Francisco, CA1 day ago $65 - $75 per hour
...and technical talent with leading AI research labs. Headquartered in San... ...-turn prompts in radiological safety, labeled as benign, dual-use, or adversarial. Evaluate AI model responses against... ...with radiological safety experts to assess misuse potential in technical...Contract workSummer workRemote workMercor
San Francisco, CA20 days ago$65 per hour
...Employers Job seekers Career centers AI Skills Studio Handshake AI Research Log in Sign up ADVERSARIAL PROMPT EXPERT Sign up now Up to $65/hr Depending on the project Bachelor... ..., while collaborating with engineers and safety researchers to share findings and improve...Hourly payPart timeRemote work10 hours per weekFlexible hoursHandshake
San Francisco, CA3 days ago$50 - $150 per hour
...hours / week Experience: 3 - 5 years Location: United States | Canada + 6 more We're hiring PhD-level experts to help train and evaluate advanced AI models. This is remote, flexible contract work where your academic expertise directly shapes how cutting-edge...Contract workTemporary workRemote workFlexible hoursBraintrust
San Francisco, CA3 days ago$90 - $150 per hour
...Job Description Job Description About the job Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers...Contract workSummer workRemote workMercor
San Francisco, CA18 days ago$65 - $75 per unit
...creative and technical talent with leading AI research labs. Headquartered in San... ...Jack Dorsey . Position: Chemicals Safety for Redteaming Type: Contract Compensation... ..., labeled as benign, dual-use, or adversarial. Evaluate model responses against defined...Contract workSummer workRemote workMercor
San Francisco, CA4 days ago$80 - $150 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...Adolescent Mental Health Clinical Advisor (AI Safety Benchmark Project) Type: Contract... ...of AI-generated conversations and provide expert judgment to calibrate automated evaluation...Contract workTraineeshipSummer workRemote work- ...building a research cohort of senior domain experts across seven specialist tracks — software/... ...formal methods and computational science, ML inference and GPU kernels, enterprise... ...technology — to help evaluate how frontier AI models reason about hard, real-world expert...Contract work
AfterQuery
San Francisco, CA15 days ago $50 - $60 per hour
...Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors... ...D'Angelo , Larry Summers , and Jack Dorsey . Position: Expert Interviewer Type: Contract Compensation: $50–$60/hour...Contract workSummer workRemote workWeekday workMercor
San Francisco, CA24 days ago- Join a leading AI lab's cutting-edge GenAI team to be at the core of the AI revolution, where your expertise fuels the development of... ...models. 1. Overview We are hiring a senior clinical medicine domain expert to work directly with a leading AI lab's research and program...Full timeContract workPart timeFreelanceLive inRelocationRelocation package
- Mercor is partnering with a leading AI research organisation to develop a clinician-informed benchmark for evaluating how AI companion chatbots respond to adolescents with mental health challenges. You will author realistic adolescent cases, assess clinical realism, and...
$60 per hour
Prolific seeks Chemistry Experts and Chemical Engineers to join our Expert Network and evaluate AI models using your chemical expertise. Successful candidates will be invited to assess and review AI-generated chemistry tasks and ensure their accuracy. Compensation can reach...Remote jobHourly payFlexible hours$60 per hour
Prolific is seeking Accountant Subject Matter Experts to join their Expert Network to provide professional insights in AI training. Responsibilities include evaluating financial documents, providing AI model guidance, and ensuring data integrity. The ideal candidates will...Remote jobHourly payWork from homeFlexible hours- ...specializing in Advanced Quantum Mechanics, Advanced Electrodynamics, or Advanced Classical Mechanics for a premier project with a top AI lab. In this role, you will contribute expertise to an AI project, creating high-quality data. You will need to hold a related PhD,...
- Mercor is seeking a Music Audio Expert - German for remote engagement with an up-to-6-month duration. Immediate start and 10+ hours per week are available. You will evaluate AI-generated lyrics and voice outputs across music categories and score training data quality to...Remote jobImmediate start10 hours per week
$100 - $150 per hour
Obsidian is hiring Employment and Labor Attorneys to train AI models with realistic workplace scenarios. This remote position requires at least 15 hours per week, with a preference for 40+ hours. The ideal candidate will have 1-4 years of experience in employment/labor...Remote job
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Expert - Adversarial ML. Be the first to apply!
Related searches
- sql expert San Francisco, CA
- fulfillment expert San Francisco, CA
- technology expert San Francisco, CA
- subject matter expert San Francisco, CA
- guest service support expert San Francisco, CA
- safety sales San Francisco, CA
- traffic safety San Francisco, CA
- patient safety associate San Francisco, CA
- patient safety assistant San Francisco, CA
- warehouse safety San Francisco, CA