AI Safety Expert - Adversarial ML
- Toronto, ON, Canada
Remote
$16 to $22 CAD / hour
Applications open in a new tab.
Job details
- Pay
- $16 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 & Marathi
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 maintain consistent testing.
- Document reproducibly by producing reports, datasets, and attack cases for customer action.
Qualifications
Must-Have
- Fluent Language Skills Required: English & Marathi. Native fluency in English and Marathi is required.
- Strong judgment about language and content accuracy.
- Rigorous attention to subtle errors and inconsistencies.
- Structured approach to guidelines and quality standards.
- Clear communication with technical and non-technical audiences.
- Adaptability across projects, task types, and customers.
Preferred
- Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Cybersecurity: penetration testing, exploit development, reverse engineering.
- Socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Creative probing: 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.
More about this job
Responsibilities
The AI Safety Expert at Mercor will test conversational AI systems by trying to break them, looking for jailbreaks, prompt injections and misuse. They will label failures, record reproducible findings and write reports and datasets for the customer.
Requirements
Candidates need native fluency in English and Marathi, strong judgment about language and content accuracy, and careful attention to small errors. Experience with adversarial ML, cybersecurity or socio-technical risk is preferred.
Skills
- Red teaming
- Jailbreak testing
- Prompt injection
- Adversarial machine learning
- RLHF
- DPO
- Model extraction
- Data annotation
- Failure classification
- Vulnerability classification
- Taxonomy-based testing
- Benchmark testing
- Report writing
- Reproducible documentation
- Penetration testing
- Exploit development
- Reverse engineering
- Socio-technical risk analysis
- Conversational AI testing
- English fluency
- Marathi fluency
- Attention to detail
- Quality standards
- Technical communication
Categories
- Technology
- Software
- Security & Safety
- Data & Analytics
Keywords
- AI safety
- red teaming
- adversarial machine learning
- jailbreak
- prompt injection
- RLHF
- DPO
- model extraction
- conversational AI
- AI red team
- LLM evaluation
- data annotation
- penetration testing
- exploit development
- reverse engineering
- harassment probing
- disinformation
- abuse analysis
- Marathi
- English
Languages
- English