Talent.com
Mercor
AI Safety Expert - Fully Remote | Upto $22/hrMercor • Sydney, New South Wales, Australia
AI Safety Expert - Fully Remote | Upto $22/hr

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

Mercor • Sydney, New South Wales, Australia
13 hours 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 & Malayalam
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 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

  • Fluent Language Skills Required: English & Malayalam. Native fluency in English and Malayalam is required.
  • Strong judgment about language and content accuracy.
  • Rigorous attention to detail and ability to notice subtle errors.
  • Structured approach to work following guidelines and quality standards.
  • Clear communication skills for technical and non-technical audiences.
  • Adaptability across projects, task types, and customers.

Preferred

  • Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
  • Cybersecurity skills: penetration testing, exploit development, reverse engineering.
  • Understanding 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: 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 - Fully Remote | Upto $22/hr • Sydney, New South Wales, Australia

Similar jobs

Game Designer

Aristocrat Technologies Australia P/LBrookvale, NSW, AU

At Aristocrat, we believe in bringing happiness to life through the power of play—a mission that drives us to build world-class gaming experiences.As a Game Designer, you will be instrumental in cr... Show more

Staff Security Engineer- AI Security (remote across Australia)

CanvaSydney, NSW, AU
Remote

Join the team redefining how the world experiences design.Hey, g'day, mabuhay, kia ora, 你好, hallo, vítejte!.We know job hunting can be a little time consuming and you're probably keen to find out w... Show more

Specialist Consultant - Psychiatry

MedrecruitCurl Curl, NSW, AU

Our client is advertising an opportunity for an Adult Addiction Psychiatrist to permanently join their team at a Clinic in NSW.The ideal start date for this position is ASAP.This private specialty ... Show more

AI Manager

GPT GROUPSydney, NSW, AU

Together, we can do great things.We shape leading experiences across office, retail, logistics and student accommodation.We’re one of Australia’s largest property groups, managing $38.Our sustainab... Show more

Cyber Threat Intel and Hunt Manager

Toll Holdings Pty Ltd (COR)Mascot, NSW, AU

At Toll, we do more than just logistics - we move the businesses that move the world.Our 16,000 team members can help solve any logistics, transport, or supply chain challenge – big or small.We hav... Show more

Threat Response Technology and Capabilities Product Owner

MasterCardSt Leonards, NSW, AU

Mastercard powers economies and empowers people in 200+ countries and territories worldwide.Together with our customers, we’re helping build a sustainable economy where everyone can prosper.We supp... Show more

Senior Designer - Entertainment

FoxtelArtarmon, NSW, AU

Join BALBOA – BALBOA is an in-house creative and production agency that helps sport and entertainment brands connect with audiences through creative that’s built by fans, for fans.We are currently ... Show more

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

Staff Applied AI Scientist

Culture AmpSydney, NSW, AU

We’re big believers in the power of IRL, so for most roles we ask Campers to work from their local Culture Amp office an average of 2 days a week to unlock connection, pace and culture together.Joi... Show more

National Estimation & Design Manager

Careerone Partner NetworkSt Leonards, NSW, AU

National Estimation & Design Manager.This is a senior technical and commercial role, responsible for guiding estimation and design teams, shaping engineering solutions, and ensuring tenders are... Show more

Remote Game Tester - Earn Extra Income!

BabkiSydney, New South Wales, Australia
Remote

Become a Professional Game Tester.We're looking for passionate gamers to join our elite team of mobile game testers.Get paid to play and test the latest games before they launch.This opportunity is... Show more

 • Promoted

Databricks Data Engineer | Mid Level

Mane ConsultingChatswood, NSW, AU

Unlock your potential with a prestigious opportunity alongside an award-winning, data-driven industry leader! A tremendous opportunity awaits a Data Engineer to collaborate a highly respected team.... Show more