Adversarial AI Specialist - Fully Remote | Upto $22/hr
- Toronto, ON, Canada
Remote
$20 to $22 CAD / hour
Applications open in a new tab.
Job details
- Pay
- $20 to $22 CAD / hour
- Workplace
- Remote
- Posting language
- English
Original 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 & Urdu
Type: Contract
Compensation: $20–$22/hour
Location: Remote
Role Responsibilities
- Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
- Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
- Document reproducibly. Produce 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 Urdu.
- 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: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Background in Cybersecurity: penetration testing, exploit development, reverse engineering.
- Expertise in socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Creative probing skills in 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.
More about this job
Responsibilities
The AI Safety Expert at Mercor will try to break conversational AI models by finding jailbreaks, prompt injections and bias problems. They will label failures, record vulnerabilities and write reproducible reports and datasets for customers.
Requirements
Candidates need native fluency in English and Urdu and prior red teaming experience in AI adversarial work, cybersecurity or socio-technical probing. Strong communication skills for explaining risks to technical and non-technical audiences are also required.
Skills
- AI red teaming
- Jailbreak testing
- Prompt injection
- Adversarial machine learning
- RLHF/DPO attacks
- Model extraction
- Bias probing
- Conversational AI testing
- Vulnerability classification
- Data annotation
- Penetration testing
- Exploit development
- Reverse engineering
- Technical report writing
- Taxonomy and benchmark application
- Urdu fluency
- English fluency
Categories
- Technology
- Software
- Consulting
- Data & Analytics
- Security & Safety
Keywords
- AI red teaming
- adversarial AI
- jailbreak
- prompt injection
- adversarial ML
- RLHF
- DPO
- model extraction
- penetration testing
- conversational AI testing
- bias exploitation
- AI safety
- LLM evaluation
- Urdu
- English
- remote contract
- AI annotation
- cybersecurity
Languages
- English
- Urdu