AI Adversarial Specialist - Fully Remote | Upto $22/hr
mercor
United KingdomPosted 17 days agoDiscoveredMatch locked
RemoteContractor
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
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 that customers can act on.
- Work
independently and asynchronously
to meet deadlines while improving
AI model performance
.
Must-Have
•
Fluent in English
and
Bengali
.
•
Prior red teaming experience in AI adversarial work
,
cybersecurity
, or socio-technical probing.
•
Preferred
•
Experience with Adversarial ML
,
Cybersecurity
, and
Socio-technical risk
.
•
Skills in Creative probing
including psychology, acting, and writing.
Application Process (Takes 20–30 mins to complete)
•
Upload resume
•
AI interview based on your resume
•
Resources & Support
•
For details about the interview process and platform information, please check
•
For any help or support, reach out to
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.
Originally posted on Himalayas
Not included in the source posting: benefits.
Skills
artificial-intelligencecybersecuritymachine-learning
Who can apply
The employer didn't state any visa, work authorization, citizenship or clearance requirements in this posting. Confirm with the employer before applying.
Read automatically from the employer's posting text. Always confirm with the employer — requirements can change after a job is published.