AI Safety Experts, English – Gujarati
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI safety red-teamer probing frontier AI models for Mercor. Testing vulnerabilities, annotating failures, and producing reproducible datasets and attack cases.
Responsibilities:
- Red-team conversational AI models and agents through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
- Generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
- Apply taxonomies, benchmarks, and playbooks to maintain consistent testing
- Produce reproducible reports, datasets, and attack cases for customers
- Review AI outputs involving sensitive topics such as bias, misinformation, and harmful behaviors
- Uncover vulnerabilities missed by automated tests
- Expand evaluation coverage and reduce production surprises
- Collaborate on projects that train and enhance frontier AI systems
Requirements:
- Fluent/native fluency in English and Gujarati required
- Strong judgment about language and content; ability to assess whether AI responses are accurate, complete, and appropriate
- Ability to identify subtle errors, inconsistencies, and gaps
- Ability to follow guidelines and quality standards consistently
- Ability to explain reasoning clearly to technical and non-technical audiences
- Adaptability across projects, task types, and customers
- Independent contractor engagement
- Must not be an H1-B or STEM OPT candidate
- Nice-to-have: adversarial ML experience, including jailbreak datasets, prompt injection, RLHF/DPO attacks, and model extraction
- Nice-to-have: cybersecurity experience, including penetration testing, exploit development, and reverse engineering
- Nice-to-have: socio-technical risk experience, including harassment/disinformation probing, abuse analysis, and conversational AI testing
- Nice-to-have: psychology, acting, or writing experience for unconventional adversarial thinking
Benefits:
- Fully remote role
- Flexible schedule / work on your own schedule
- Weekly payments via Stripe or Wise
- Participation in higher-sensitivity projects is optional
- Clear guidelines and wellness resources for sensitive-content work
- Competitive pay
- Reasonable accommodations upon request
- Referral opportunity earning up to $90 per successful referral (subject to limits)
Similar Jobs
Director, AI Data Operations
Director building Bill Gosling Outsourcing’s AI Data Operations practice. Developing scalable AI services, partnerships, client solutions, and revenue streams for global delivery.
Behavioral Health Expert – AI Safety, Model Evaluation
Behavioral health experts evaluating sensitive AI conversations for leading AI labs. Defining safe, neutral responses and improving model judgment.
Senior Manager, AI Business Modernization
AI modernization leader advancing Hershey’s U.S. snacks business through AI products, agentic solutions, and measurable productivity gains. Driving adoption, governance, and value realization across functions.
Engineer III, AI SDLC Engineer
AI SDLC Engineer building agentic workflows for CrowdStrike’s cybersecurity platform. Improving developer productivity through LLM infrastructure, observability, model routing, and benchmarks.
Working Student, Sales Operations & AI
Working student supporting PTV Logistics, a transportation logistics software company, with AI-driven sales operations. Building analytics, improving CRM data quality, and optimizing business processes.
AI Quality & Evaluation Lead
AI evaluation lead building quality rubrics and validating judges for Samsung Health’s generated coaching. Samsung Food connects food, health, and home through personalized digital experiences.
Manager – Transformation & Process Design, AI, Agentic Organization
Transformationsmanager gestaltet KI-Agentenorganisation und KI-gestützte Prozesse bei Meliorate, einer Managementberatung für asset-intensive Unternehmen. Aufbau von Governance, Workflows und Veränderungskompetenzen.
AI Automation Expert – Microsoft M365, Copilot
AI Automation Expert building Microsoft 365, Copilot Studio, and Power Automate solutions. Delivering workshops and practical AI automation for mid-sized businesses.
Co-Founder – Tech Partner, AI, Open Source
Technical co-founder building open-source AI and data infrastructure in Estonia. Designing platform architecture, AI integrations, and ERP adapters while shaping product strategy and startup partnerships.
Generative AI Artist
Generative AI Artist creating AI-driven visuals, sequences, and previs for Rodeo FX’s visual-effects and advertising productions. Building ComfyUI workflows and collaborating with compositing, 3D, and art-direction teams.
Account-Based Marketing Strategist – Train AI
ABM Strategist shaping account-specific marketing for RWS TrainAI’s enterprise AI data services. Driving personalized campaigns, sales enablement, and measurable account growth.
Applied AI Sales Executive
Applied AI Sales Executive selling Cloudera-supported Mistral enterprise AI solutions. Owning complex enterprise deals from proof of concept through expansion across Cloudera data estates.
AI and Innovation Intern
Estagiário(a) explorando agentes de IA generativa, LLMs e dados na Zup Innovation. Testando soluções para otimizar processos e criar produtos digitais.
Analyst – Commercial Contract Administrator, Analytics, Automation & AI Innovation
Commercial contract administrator processing pharmaceutical rebates and detecting revenue leakage. Using SQL, Excel, Power BI, and AI automation to improve Lilly’s payment operations.
AI Transformation Office Lead
JLL AI transformation leader establishing a global office to implement AI across real estate services. Delivering enterprise-scale savings through platforming and operational optimisation.
AI Automations Specialist
AI automation specialist building agents, workflows, and outreach systems for a personal financial advisor. Managing award travel, customer calls, prospecting, and executive support remotely.
Enterprise AI Administrator – GenAI, Copilot, SaaS Platforms
Ford AI Platform Administrator managing enterprise Copilot, Gemini, and Anthropic platforms. Securing AI governance, agent lifecycles, compliance, usage, and operational reliability.
Head of AI Expansion
Head of AI Expansion driving global adoption of Tether’s QVAC and decentralized AI infrastructure. Building enterprise, government, and technology partnerships for privacy-preserving AI.
Head of AI Expansion
Head of AI Expansion driving global adoption of Tether’s QVAC and decentralized AI ecosystem. Building strategic partnerships, go-to-market execution, and a worldwide AI expansion team.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor. Designing adversarial prompts and documenting vulnerabilities to improve model safety and alignment.