Talent.com
Mercor
AI Safety Expert - Red TeamingMercor • Sydney, New South Wales, Australia
No longer accepting applications
AI Safety Expert - Red Teaming

AI Safety Expert - Red Teaming

Mercor • Sydney, New South Wales, Australia
15 days ago
Job type
  • Remote
  • Quick Apply
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 & Odia
Type: Contract
Compensation: $20–$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 maintain consistent testing.
  • Document reproducibly to produce reports, datasets, and attack cases for customer action.
  • Work independently and asynchronously to meet deadlines while improving AI model performance.

Qualifications

Must-Have

  • Fluent Language Skills Required: English & Odia.
  • Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
  • Strong communication skills to explain risks to technical and non-technical stakeholders.

Preferred

  • Experience in Adversarial ML, Cybersecurity, or Socio-technical risk.
  • Skills in Creative probing such as psychology, acting, or 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: https://talent.docs.mercor.com/welcome
  • For any help or support, reach out to: support@mercor.com

PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.

Create a job alert for this search

AI Safety Expert - Red Teaming • Sydney, New South Wales, Australia

Similar jobs

Data Privacy & Governance Lead for Risk & AI Initiatives

ASXSydney, AU

ASX is seeking a Data Privacy Specialist with significant experience in data privacy and strong knowledge of the Australian Privacy Act and GDPR.This role involves providing expertise in data priva... Show more

 • Promoted

Technical Team Lead (Fullstack+ AI integration)

PeoplebankSydney, AU

Technical Team Lead (Fullstack+ AI integration).Technical Team Lead (Fullstack+ AI integration).Technical Team Lead (Fullstack+ AI integration).Be among the first 25 applicants.Technical Team Lead ... Show more

 • Promoted

AI Platform Expert & Incident Architect (Sydney)

LegoraSydney, AU

Legora is seeking a Senior Platform Specialist who will own the hardest technical escalations and drive root-cause analysis across the platform.You will validate platform behavior before release, i... Show more

 • Promoted

Operational Risk Senior Analyst | Technology, Cyber, Data and AI

Macquarie GroupSydney, AU

Our Risk Management Group provides independent oversight and advice to help ensure Macquarie’s Banking and Financial Services business operates safely, securely, and within risk appetite.Working ac... Show more

 • Promoted

Manager, Digital Risk & AI Audit Leader

EYSydney, AU

At EY, we’re all in to shape your future with confidence.We’ll help you succeed in a globally connected powerhouse of diverse teams and take your career wherever you want it to go.Join EY and help ... Show more

 • Promoted

Remote Psychology QA Lead — Elevating AI Safety & Accuracy

YO IT ConsultingSydney, AU
Remote

YO IT Consulting is hiring a Psychology Quality Assurance Lead for a remote contractor role.The position involves overseeing quality across psychology AI projects, reviewing content for accuracy an... Show more

 • Promoted

Director, Cyber Resilience & AI-Enabled Advisory

Grant Thornton InternationalSydney, AU

Grant Thornton Australia is seeking a Director to lead cyber resilience advisory, blending deep cybersecurity expertise with the emerging frontier of AI-enabled professional services delivery.You w... Show more

 • Promoted

Remote AI Verification Specialist, CS Expert

ProlificSydney, AU
Remote

A leading AI evaluation firm is seeking an AI Trainer for a fully remote opportunity.You will review Computer Science research papers and ensure that LLM-generated graphical abstracts maintain scie... Show more

 • Promoted

Project Manager - AI Data Operation (Safety), Trust and Safety - Sydney

TikTokSydney, AU

Manage the end-to-end operations of labeling projects and uphold efficiency and quality by preparing and monitoring key project metrics.Leverage business platforms and other tools to effectively mo... Show more

 • Promoted

Lead AI Developer

ELMO SoftwareSydney, AU

AI solutions that automate complex HR processes, enhance employee experiences, and deliver unprecedented business intelligence.This isn't just another AI engineering role; it's an opportunity to pi... Show more

 • Promoted

Senior Data Scientist, Trust & Safety — Build Risk Metrics

LinktreeSydney, AU

Linktree is seeking a Senior Data Scientist to strengthen trust and safety across the platform.You will define harm measurements, assess risk, and shape mitigation strategies while partnering with ... Show more

 • Promoted

Enterprise SDR – AI Security & Cyber Growth (ANZ)

TrendMicroSydney, AU

TrendAI, the AI security leader and enterprise unit of Trend Micro, seeks a motivated Sales Development Representative to build a high-quality pipeline across enterprise and mid‑market accounts in ... Show more

 • Promoted

Remote Applied AI Engineer - Build End-to-End AI Agents

LinktreeSydney, AU
Remote

Linktree is hiring an Applied AI Engineer to turn frontier model capabilities into useful, trustworthy product experiences for creators, businesses, and their audiences.You’ll work across product, ... Show more

 • Promoted

AI Governance Lead — Responsible AI & Risk Compliance

Cuscal LimitedSydney, AU

A pioneering payments company in Sydney is looking for an AI Governance Lead to help deliver innovative solutions.This role focuses on ensuring AI is used safely and responsibly, managing risks, an... Show more

 • Promoted

Senior QA Engineer - AI Security, Flexible Work Environment

Future Secure AISydney, AU

Future Secure AI (FSAI) is looking for a Senior Quality Assurance Engineer to ensure their AI products meet high-quality standards.This role involves collaborating with development teams, thorough ... Show more

 • Promoted

Principal Enterprise AI Risk

AMP - GeneralSydney, NSW, AU

If you live in Australia or New Zealand, you’ve likely heard of AMP.But at a time when society is changing, we are too.We’re now a nimbler business with new leadership and thinking.For us, these ar... Show more

Manager – AI Risk

Macquarie GroupSydney, AU

Join our Global Non-Financial Risk team based in Sydney as a Manager where you will join a team at the forefront of enabling innovation, creating an ethical environment that allows Macquarie to har... Show more

 • Promoted

Operational Risk Senior Analyst | Technology, Cyber, Data and AI

Macquarie Bank LimitedSydney, AU

Operational Risk Senior Analyst | Technology, Cyber, Data and AI.Our Risk Management Group provides independent oversight and advice to help ensure Macquarie’s Banking and Financial Services busine... Show more

 • Promoted

AI Safety Expert - Red Team

MercorSydney, New South Wales, Australia
Remote
Quick Apply

Headquartered in San Francisco, our investors include.AI Safety Experts — English & Odia.Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.Generate high-quality human d... Show more

AI Safety Specialist - Fully Remote | Upto $22/hr

MercorSydney, New South Wales, Australia
Remote
Quick Apply

Headquartered in San Francisco, our investors include.AI Safety Experts — English & Odia.Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.Generate high-quality human d... Show more