AI Safety Expert - Adversarial ML

Mercor · Bengaluru

  • Experience1–2 yrs
  • SalaryDisclosed
  • Work moderemote
  • Posted26 Sept 2026
Apply for this job

About Mercor

Mercor is hiring in Bengaluru in technology software. This role looks for around 1+ years of experience.

Skills

  • English
  • Kannada
  • human data annotation
  • taxonomies
  • benchmarks
  • playbooks
  • quality standards

The role

A trust and safety associate at an artificial intelligence research marketplace identifies jailbreaks, prompt injections, misuse cases, and bias exploitation through adversarial machine learning and cybersecurity, and produces reproducible attack cases. The work also applies socio-technical risk analysis and human data annotation to improve conversational AI models.

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 & Kannada

Type: Contract

Compensation: $16–$22/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 for customer action.Work independently and asynchronously to meet deadlines while improving AI model performance.

Qualifications

Must-Have

Native fluency in English and Kannada.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 skills for technical and non-technical audiences.Adaptability across projects, task types, and customers.

Preferred

Experience with Adversarial ML, Cybersecurity, and socio-technical risk analysis.Skills in creative probing such as psychology, acting, or 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.