AI Safety Expert - Adversarial ML at Mercor | Rozgoo | Rozgoo

Mercor

London, GB · Remote · Contract

AI Safety Expert - Adversarial ML

₹57.7L – ₹57.7LPosted 21 days ago

Location: London, GB
Work mode: Remote
Employment: Contract
Salary: ₹57.7L – ₹57.7L
Experience: Mid-level

About the role

© 2026 Rozgoo

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. Ge…

Requirements

experience in adversarial machine learning or AI safety
knowledge of conversational AI systems
ability to identify security vulnerabilities

Skills

adversarial machine learning
ai safety
red teaming
prompt injections
bias exploitation
conversational ai
jailbreak testing
contract work
remote work
english proficiency
bengali proficiency

About the company

Mercor

Posted via Adzuna

How to apply

Apply Now takes you to Rozgoo, where auto-apply can submit your application for this role. Updated today.

Mercor

AI Safety Expert - Adversarial ML

₹57.7L – ₹57.7L