AI Safety Specialist - Fully Remote | Upto $22/hr
- 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 & Bengali
Type: Contract
Compensation: $16–$22/hour
Location: Remote
Role Responsibilities
- Red team conversational AI models and agents. Perform jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
- Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
- Document reproducibly to 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 Bengali.
- Strong judgment about language and content accuracy.
- Rigorous attention to subtle errors and inconsistencies.
- Ability to work to guidelines and quality standards consistently.
- Clear communication with 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.
- Socio-technical risk expertise: 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.
More about this job
Responsibilities
The AI Safety Specialist at Mercor will test chatbots and AI agents by trying to make them fail or misbehave. They will record the failures, sort them by type of risk, and write clear reports the customer can act on.
Requirements
Mercor needs native-level English and Bengali, strong judgment on language and content accuracy, and careful attention to small errors. Experience with adversarial machine learning or cybersecurity is preferred.
Skills
- Red teaming of conversational AI
- Jailbreak and prompt injection testing
- Adversarial machine learning
- RLHF and DPO attacks
- Model extraction
- Bias exploitation
- Failure annotation and classification
- Taxonomy and benchmark-based testing
- Reproducible documentation
- Penetration testing
- Exploit development
- Reverse engineering
- Harassment and abuse analysis
- Disinformation probing
- Native English
- Native Bengali
- Asynchronous independent work
- Adaptability across projects
Categories
- Technology
- Software
- Data & Analytics
Keywords
- AI safety
- red teaming
- jailbreak
- prompt injection
- adversarial machine learning
- AI red team
- LLM evaluation
- RLHF
- DPO
- model extraction
- penetration testing
- exploit development
- reverse engineering
- AI data annotation
- Bengali
- English
- bias testing
- conversational AI testing
- remote contract
- AI trainer
Languages
- English
- Bengali