AI Safety Expert - Adversarial ML

Mercor · India

  • Experience0–1 yrs
  • SalaryDisclosed
  • Work moderemote
  • Levelfresher
  • Posted18 Sept 2026
Apply for this job

About Mercor

Mercor is hiring in India in technology software. This role looks for around 0+ years of experience.

Skills

  • English
  • Marathi
  • Adversarial ML
  • Conversational AI Testing
  • Jailbreak Testing
  • Prompt Injection
  • Human Data Annotation
  • Vulnerability Classification
  • Risk Taxonomies
  • Quality Standards

The role

An AI safety expert at a technology talent marketplace red-teams conversational AI models through Adversarial ML and Penetration Testing, generating structured human data with English and Marathi. The role applies Model Extraction and analyzes misuse risks for technical and non-technical audiences.

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 & Marathi

Type: Contract

Compensation: $16–$22/hour

Location: Remote

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 for customer action.

Qualifications

Must-Have

Fluent Language Skills Required: English & Marathi. Native fluency in English and Marathi is required.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

Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.Cybersecurity: penetration testing, exploit development, reverse engineering.Socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.Creative probing: 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.

,