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 & Gujarati
Type: Contract
Compensation: $16–$22/hour
Location: Remote
Role Responsibilities
- Red team conversational AI models and agents by identifying jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
- Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
- Document reproducibly by producing 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 Gujarati .
- Strong judgment about language and content accuracy, completeness, and appropriateness.
- Rigorous attention to detail, noticing subtle errors and inconsistencies.
- Ability to work to guidelines and quality standards consistently.
- Clear communication skills for technical and non-technical audiences.
- Adaptability across projects, task types, and customers.
Preferred
- Experience with Adversarial ML : jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Background in Cybersecurity : penetration testing, exploit development, reverse engineering.
- Understanding of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Skills in creative probing: 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.
$16 - $22 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Experts — English & Telugu Type: Contract... ...customers. Preferred Experience in Adversarial ML : jailbreak datasets, prompt injection...SuggestedContract workSummer workRemote work$65 - $70 per hour
...Biology Expert (PhD) — AI Safety is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and... ...systems, security research, or adversarial ML work for Biology Expert (PhD) — AI Safety...SuggestedFor contractorsRemote work10 hours per week$48 - $52 per hour
...to help make advanced AI models safer. You'll apply... ...in German. No prior AI/ML experience is required... .... What you'll do Write expert-level prompts in German... ...conversations. Flag adversarial phrasings and escalation... ...Background in trust and safety, content moderation, policy...SuggestedPart timeImmediate start$61 - $65 per hour
About the role Bilingual Danish STEM Expert (PhD) — AI Safety is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document... ..., security research, or adversarial ML work for Bilingual Danish STEM Expert (...SuggestedFor contractorsRemote work10 hours per week$48 - $62 per hour
...technical talent with leading AI research labs. Headquartered... ...and Jack Dorsey . Position: AI Safety Experts — English & Swedish Type:... ...red teaming experience in AI adversarial work , cybersecurity , or socio... ...* Experience in Adversarial ML , Cybersecurity , or socio-technical...SuggestedContract workSummer workRemote work$17 - $25 per hour
...technical talent with leading AI research labs. Headquartered... ...and Jack Dorsey . Position: AI Safety Experts — English & Vietnamese Type:... ...red teaming experience in AI adversarial work , cybersecurity , or... ...Experience with Adversarial ML , Cybersecurity , or socio-technical...Contract workSummer workRemote work$48 - $62 per hour
...technical talent with leading AI research labs. Headquartered... ...Jack Dorsey . Position: AI Safety Experts — English & Dutch Type:... ...experience in red teaming (AI adversarial work, cybersecurity, socio-... ...Experience in Adversarial ML : jailbreak datasets, prompt...Contract workSummer workRemote work- ...financial enterprise and we are building AI agents that serve millions of customers directly... ..., with the reliability, latency, and safety bar that implies. We're engaging senior... ...shipped. Strong Python (primary agent/ML stack) and Java (service integration) both...For contractors
$40 per hour
...years experience About the Role Pasiflora AI has immediate openings for Chemical AI Safety Annotators & Subject Matter Experts to evaluate AI-generated responses in chemistry... ...Classify content as Benign, Dual-Use, or Adversarial Assess technical accuracy and safety...For contractorsImmediate startRemote work$70 - $84 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...Larry Summers, and Jack Dorsey. Position: AI Safety Red TeamerType:ContractCompensation:$70-$... ...hourLocation:Remote Role Responsibilities Design adversarial prompts to stress-test frontier AI models...Summer workRemote work$40 per hour
Pasiflora AI seeks experienced chemistry professionals for remote Independent Contractor roles as Chemical AI Safety Annotators & Subject Matter Experts. You will evaluate AI responses in chemistry and safety, classify content, write expert references, and help calibrate...Remote jobFor contractors$62.5 per hour
HVAC Expert for AI Diagnostics and System Design Build HVAC diagnostic and system-design scenarios, write reference answers, and rate AI responses for accuracy and safety. This remote contractor role requires EPA Section 608 certification and at least 20 hours per week....Hourly payContract workPart timeFor contractorsRemote workFlexible hours$85 per hour
...Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include... ...D'Angelo , Larry Summers , and Jack Dorsey . Position: ML Engineer (Coding Agent Experience) Type: Contract Compensation...Contract workSummer workRemote work$90 per hour
...Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include... ...Responsibilities Evaluate frontier AI models on coding, ML , and analysis tasks to identify vulnerabilities and failure modes...Remote jobContract workSummer work- Joinkeywork is seeking a chemistry reviewer to validate AI-generated chemistry content. You will write problems, review peers, and assess mechanisms, stoichiometry, and procedures for safety. Strong written English and ability to justify conclusions are essential. You...Remote work
$37 per unit
...technical talent with leading AI research labs. Headquartered in... ...Dorsey . Position: AI Safety Specialist Type: Contract... ...Collaborate with subject matter experts to ensure consistency,... ..., policy evaluation , or adversarial testing Comfort working independently...Contract workSummer workRemote work- Health Expert — Healthcare AI Output Reviewer is a remote clinical-review track for evaluating AI outputs that touch clinical review. Reviewers... ...reasoning, dosing logic, and guideline adherence; flag patient-safety issues; and document the corrected clinical reasoning so the...Hourly payFor contractorsRemote work10 hours per week
- Invisible Technologies Inc. seeks an AI QA trainer to harden model reasoning and reliability across multilingual and domain-specific... ...build rubrics, and document failure modes to raise standards for safety, bias checks, and prompt robustness. As a contractor, you will work...Remote jobFor contractorsFlexible hours
- ...platform for finding and building careers in AI training and data labeling. OpenTrain AI... ...a Film and Television AI Evaluation Expert to create challenging, domain-specific prompts... ...cases. Develop benchmark datasets and adversarial test cases. Provide evidence-based feedback...Part timeFor contractorsRemote workFlexible hours
$35 - $42 per hour
...modeling, mergers & acquisitions (M&A), corporate finance, and capital markets. In this role, you will evaluate AI-generated financial content and provide expert feedback to improve financial reasoning and analytical accuracy. Help Shape the Future of AI in Finance Volga...Hourly payExtra incomePermanent employmentContract workTemporary workPart timeImmediate startRemote workFlexible hours$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 work$65 - $75 per unit
...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 work$140 per hour
...technical talent with leading AI research labs. Headquartered in... ...technical feedback. Design adversarial tasks and red teaming... ...Develop rubrics to assess the safety, accuracy, and harm potential... ...Collaborate with other subject matter experts to ensure consistency and...Remote jobContract workPart timeSummer workWeekday work$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$65 - $75 per unit
...technical talent with leading AI research labs. Headquartered in... ...Dorsey . Position: Radiation Safety Officer Type: Contract Compensation... ...as benign, dual-use, and adversarial. * Evaluate model responses against... ..., published research, or expert witness experience. Application...Contract workSummer workRemote work$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 work$24 per hour
...Use your accounting and QuickBooks experience to help improve AI responses to real small-business and financial questions. In this remote freelance project, you'll evaluate accuracy, identify gaps and help build reliable standards for accounting-related AI tasks. A part...Part timeFreelanceRemote work$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 week- We Are:Accenture is helping companies use generative AI and semantic layer to reinvent their enterprise and optimize business functions... ...Engineering, Mathematics, or a related field.Broad experience in diverse ML techniques and agentic systems.Compensation at Accenture varies...Work experience placementLive inWork at officeLocal area
- ...Key Responsibilities Train and improve AI models by annotating and labeling data specific to organic and inorganic chemistry. Review and validate AI-generated content for accuracy and relevance. Provide domain-specific knowledge to enhance AI model performance...Temporary workFlexible hours
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Expert - Adversarial ML. Be the first to apply!
- sql expert New York, NY
- technology expert New York, NY
- fulfillment expert New York, NY
- guest service support expert New York, NY
- subject matter expert New York, NY
- safety sales New York, NY
- entry level safety specialist New York, NY
- safety technician New York, NY
- safety valve technician New York, NY
- traffic safety New York, NY





