AI Safety Expert - Red Team
- Toronto, ON, Canada
Remote
$48 to $62 CAD / hour
Applications open in a new tab.
Job details
- Pay
- $48 to $62 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 & Finnish
Type: Contract
Compensation: $48–$62/hour
Location: Remote
Role Responsibilities
- Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
- 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 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 Finnish.
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Strong communication skills to explain risks clearly to technical and non-technical stakeholders.
- Ability to thrive on moving across projects and customers.
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: 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 probe AI models for jailbreaks, prompt injections, misuse and bias, then label failures and document reproducible attack cases. The work follows set taxonomies and playbooks and is delivered as reports and datasets.
Requirements
Candidates need native fluency in English and Finnish and prior red teaming experience in AI adversarial work, cybersecurity or socio-technical probing. Strong communication skills for technical and non-technical audiences are also required.
Skills
- Red teaming
- Jailbreak testing
- Prompt injection
- Adversarial machine learning
- RLHF
- DPO
- Model extraction
- Penetration testing
- Exploit development
- Reverse engineering
- Abuse analysis
- Disinformation probing
- Conversational AI testing
- Taxonomy-based classification
- Data annotation
- Technical report writing
- Risk communication
- Native Finnish
- Native English
- Asynchronous work
Categories
- Technology
- Security & Safety
- Data & Analytics
- Software
Keywords
- AI red teaming
- AI safety
- jailbreak
- prompt injection
- adversarial ML
- RLHF
- DPO
- model extraction
- penetration testing
- exploit development
- reverse engineering
- socio-technical risk
- conversational AI testing
- abuse analysis
- disinformation
- Finnish
- English
- remote contract
- AI evaluation
- data annotation
Languages
- English