AI Safety Experts – English, Malay
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI red teaming expert probing frontier models for Mercor, which partners with AI labs and enterprises to train advanced models. Generating reproducible attack data and vulnerability reports to improve AI safety and robustness.
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 keep testing consistent
- Produce reproducible reports, datasets, and attack cases for customers
- Probe AI systems to uncover vulnerabilities automated tests miss
- Expand evaluation coverage and reduce production surprises
- Support Mercor customers in improving the safety and robustness of their AI systems
Requirements:
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Ability to push systems to breaking points through adversarial testing
- Experience using frameworks or benchmarks rather than random hacks
- Ability to explain risks clearly to technical and non-technical stakeholders
- Adaptability across projects and customers
- Native fluency in English and Malay
- Adversarial ML experience such as jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction is a nice-to-have
- Cybersecurity specialties such as penetration testing, exploit development, or reverse engineering are a nice-to-have
- Socio-technical risk specialties such as harassment/disinformation probing, abuse analysis, or conversational AI testing are a nice-to-have
- Creative probing experience in psychology, acting, or writing is a nice-to-have
- Must not be an H1-B or STEM OPT candidate
Benefits:
- Fully remote role
- Flexible own schedule
- Higher-sensitivity project participation is optional
- Clear guidelines and wellness resources for sensitive-content projects
- Weekly payments via Stripe or Wise
- Opportunity to build experience in human data-driven AI red teaming
- Direct role in making AI systems more robust, safe, and trustworthy
- Competitive pay
- Collaboration with leading researchers
Similar Jobs
Technical AI Quality Coordinator
Technical AI Quality Coordinator improving AI data quality for RWS’s global content and language services. Automating checks, building testing frameworks, and monitoring annotation and model-evaluation pipelines.
Director of AI and Educational Technology
Teach For All leader advancing global teacher-workforce policy and government partnerships. Building coalitions and supporting network partners across eligible remote locations.
Working Student AI Transformation
Working student helping casavi, a German PropTech company, turn AI ideas into practical tools and workflows. Supporting internal AI adoption across property-management software teams.
AI Safety Expert, English, Danish
AI red team expert attacking conversational models for Mercor, which partners with AI labs and enterprises to train frontier systems. Generating reproducible vulnerability data, attack cases, and safety evaluations for customers.
Workflow & AI Agent Engineer
Workflow and AI Agent Engineer supporting Chatarmin’s B2B e-commerce SaaS clients. Owning onboarding, support, API/LLM solutions, and product feedback loops.
AI Strategy – Digital Implementation
Werkstudent:in entwickelt Website, App und Klinik-Dashboard für Xeno Patchs wachsendes MedTech-Produktportfolio. Integration digitaler Bausteine, Feature-Tests und schnelle KI-gestützte Umsetzung neuer Funktionen.
Senior Analyst, Artificial Intelligence
Analista Sênior criando soluções de IA, LLMs e pipelines de dados para a digitalização industrial da Vetta. Projetando arquiteturas escaláveis em Databricks, AWS e Azure para otimizar operações e apoiar a descarbonização.
Senior Manager – AI Strategy and Execution
AI Strategy & Execution Senior Manager helping Elliott Davis consulting clients turn AI into measurable business value. Leading AI roadmaps, governance, workflows, transformation, and client engagements end to end.
AI Literacy Manager
AI literacy manager scaling responsible AI education at Amgen, a biotechnology company developing innovative human therapeutics. Leading enterprise training, engagement, adoption, and go-to-market programs.
Senior Developer, Artificial Intelligence
Desenvolvedor(a) sênior criando aplicações LLM, copilots e agentes para a consultoria tecnológica SEIDOR. Integrando IA, APIs, dados e arquiteturas GenAI.
Agency Director – AI, Systems, Straight Talk
Agenturleiter für CAMPUS FÜR DIGITALE WERTE, Anbieter digitaler Marketing- und Erfahrungsberichte-Lösungen. Führung, KI-Integration, Plattformsteuerung, Vertrieb und KPI-gesteuerte Skalierung der Agentur.
Desarrollador/a – Producto AI Conversacional, AI-First
Desarrollador/a diseñando sistemas conversacionales AI-first para Yalfer. Integrando LLMs, agentes y flujos escalables con Python, Next.js y AWS.
Head of AI Safety
Head of AI Safety leading Moonshot's applied AI safety portfolio across violence, extremism, child safety, and crisis risks. Advising frontier AI companies, governments, and regulators through evaluations, interventions, and team leadership.
Head of AI Safety
Head of AI Safety leading applied AI system evaluations and advisory work at Moonshot. Managing teams, partnerships, and portfolio growth across violence prevention and online harms.
AI Agent Evaluator
Evaluating Hippocratic AI’s clinical agents for symptom triage, diabetes medication titration, and travel health guidance. Providing safety-focused feedback to improve AI-driven healthcare tools.
Sustainability Metrics Governance, AI Specialist
Sustainability metrics specialist improving ESG data governance and AI-enabled reporting at GE Vernova. Monitoring KPIs, validating disclosures, and deploying scalable automation solutions.
Generative AI Analyst, Portuguese
Generative AI Analyst reviewing Portuguese AI content for Welo Data’s global AI training systems. Annotating multimedia data and performing quality checks to improve advanced AI datasets.
AI User Interview Specialist
Paid 60-minute Terac interview examining how professionals use generative and analytical AI tools. Sharing workflow pain points and proposing future capabilities for AI products.
Director, AI and Technology Enablement
Director leading Salesforce, AI workflow, and technology enablement for TMG, a leadership advisory firm. Translating business priorities into practical systems, data processes, vendor implementations, and user adoption.
Internship – AI-Based Semantic Mapping for Autonomous Driving
CARIAD automotive software intern researching radar-camera fusion and semantic mapping for autonomous driving. Developing and evaluating multimodal perception methods for complex vehicle environments.