AI Safety Expert - Red Team

Mercor · Mumbai Metropolitan Region

  • Experience3–4 yrs
  • SalaryDisclosed
  • Work moderemote
  • Posted29 Sept 2026
Apply for this job

About Mercor

Mercor is hiring in Mumbai Metropolitan Region in technology software. This role looks for around 3+ years of experience.

Skills

  • English
  • Assamese
  • Adversarial ML
  • prompt injection
  • jailbreaks
  • bias exploitation
  • taxonomies
  • benchmarks
  • playbooks

The role

An AI safety expert at an AI research marketplace red-teams conversational AI models and agents through adversarial machine learning and penetration testing, classifies vulnerabilities and systemic risks, and produces reproducible attack cases and datasets. The role applies prompt injection analysis and jailbreak testing to improve model safety.

Full 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 & Assamese

Type: Contract

Compensation: $16–$22/hour

Location: Remote

Role Responsibilities

Red team conversational AI models and agents. Focus on 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 maintain consistent testing.Document reproducibly. 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 Assamese.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

Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks.Cybersecurity skills: penetration testing, exploit development, reverse engineering.Knowledge of socio-technical risk: harassment/disinfo probing, abuse analysis.Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.

Application Process (Takes 20–30 mins to complete)

Upload resumeAI interview based on your resumeSubmit form

Resources & Support

For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcomeFor 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.