Log in Sign up free
Apply now

First seen by our source: 19 days ago

AI Safety Expert - Adversarial ML

@ Mercor

View all jobs Website

Toronto, Ontario

$16–$22/hr
Apply now
SIGNALS

Overview

Mercor is hiring AI Safety Experts fluent in English and Bengali on a contract basis at $16–$22 per hour, remote. The work is red-teaming conversational AI models and agents through jailbreaks, prompt injections, misuse cases and bias exploitation, then documenting findings.

Pay:

$16–$22 an hour

Responsibilities:

  • Red team conversational AI models and agents
  • Annotate failures and classify vulnerabilities
  • Follow taxonomies, benchmarks and playbooks
  • Produce reproducible reports and attack datasets
  • Work independently and asynchronously

Requirements summary:

  • Native fluency in English and Bengali
  • Strong judgment about language and content
  • Rigorous attention to detail and structure
  • Excellent communication for technical and non-technical audiences
  • Adaptability across projects and customers
  • Preferred: adversarial ML or cybersecurity experience

Tools & skills

MLResearchWork independentlyAttention to detailCommunication skillsAdaptabilityCybersecurityPenetration testingReverse engineering
Source and dates

Source type not verified · manatal

Employer posting date
Not provided
First seen by our source
2026-10-18
Source record updated
2026-10-18

These dates describe the source record, not a live verification that the employer is still hiring. Check the original posting.

Job details

DepartmentQuality assurance
Travelair: none · ground: none
Work settingHome
PositionMostly sitting
Physical demandsphysical low · computer high
LanguagesEnglish, Bengali

Summary and details written by AI from the posting; the employer’s posting is the authority.

Apply now

Mercor

Saved company profile

Historical company information from a saved The Jobs API profile (LinkedIn/Crunchbase fields). It is not live-verified; figures may have changed. Missing values remain unknown.

We connect human expertise with leading AI labs and enterprises to train frontier models.

Full company description

Mercor is defining the future of work. We connect human expertise with leading AI labs and enterprises to train frontier models.

LinkedIn followers
654,507
People associated on LinkedIn
5,250
Reported office locations
  • San Francisco, California 94105, US
Business categories
  • Employment
  • Software
  • Recruiting
  • Data Collection and Labeling
  • Artificial Intelligence (AI)
  • Machine Learning
Other recorded names
  • Mercor
Profile identifies a recruitment agency
Yes
Reported total investment
483,600,000

Currency and observation date were not supplied; this is not a current valuation or a funding round.

View all jobs Website

Mercor is defining the future of work. We connect human expertise with leading AI labs and enterprises to train frontier models.

FieldValue
IndustrySoftware Development
Company size51-200 employees
HeadquartersSan Francisco, California
Organization typePrivately Held
Year founded2023
Open jobs on Jobsy1,626
LinkedInView page
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 & Bengali
Type: Contract
Compensation: $16–$22/hour
Location: Remote

Role Responsibilities

  • Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
  • Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
  • Apply structure. Follow taxonomies, benchmarks, and playbooks to keep testing consistent.
  • Document reproducibly. Produce reports, datasets, and attack cases customers can act on.
  • Work independently and asynchronously. Thrive in flexible hours while improving AI model performance.

Qualifications

Must-Have

  • Native fluency in English and Bengali.
  • Strong judgment about language and content.
  • Rigorous attention to detail and structure.
  • Excellent communication skills for technical and non-technical audiences.
  • Adaptability across projects, task types, and customers.

Preferred

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

Application Process (Takes 20–30 mins to complete)

  • Upload resume
  • AI interview based on your resume
  • Submit form

Resources & Support

  • For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome
  • For any help or support, reach out to: [email protected]

PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.

Similar jobs

  • AI Safety Expert - Red Team

    Toronto, ON
    $48–$62/hr

    Mercor

    Candidates need native fluency in English and Finnish and prior red teaming experience in AI adversarial work, cybersecurity or socio-technical probing. They must explain risks clearly to both technical and non-technical people.

    Research, Work independently, Meet deadlines, Cybersecurity, Communication skills, ML

    AI Safety Expert - Bilingual

    Toronto, ON
    $16–$22/hr

    Mercor

    Candidates need native fluency in English and Punjabi, strong judgment about language and content, and careful attention to detail. Structured work that follows guidelines and clear written communication are also required.

    Bilingualism, Research, Work independently, Meet deadlines, Attention to detail, Communication skills

    AI Safety Expert - Adversarial ML

    Toronto, ON
    $16–$22/hr

    Mercor

    Candidates need native fluency in English and Kannada, strong judgment about language accuracy, and a careful eye for subtle errors. Adversarial ML or cybersecurity experience is preferred.

    ML, Research, Communication skills, Adaptability, Cybersecurity, Penetration testing

    AI Safety Expert - Adversarial ML

    Toronto, ON
    $16–$22/hr

    Mercor

    Mercor needs native fluency in English and Odia, strong judgment about language accuracy, and careful attention to subtle errors. Adversarial ML or cybersecurity experience is preferred.

    ML, Research, Work independently, Meet deadlines, Communication skills, Adaptability

    AI Safety Expert - Adversarial ML

    Toronto, ON
    $16–$22/hr

    Mercor

    Candidates need native fluency in English and Assamese, strong judgment about language and content accuracy, and careful attention to small errors. Experience in adversarial ML or cybersecurity is preferred.

    ML, Research, Work independently, Communication skills, Adaptability, Cybersecurity

    AI Safety Expert - Adversarial ML

    Toronto, ON
    $16–$22/hr

    Mercor

    Mercor needs native fluency in English and Odia, strong judgment about language accuracy, and careful attention to subtle errors. Adversarial ML or cybersecurity experience is preferred.

    ML, Research, Work independently, Meet deadlines, Communication skills, Adaptability

    AI Safety Expert - Adversarial ML

    Toronto, ON
    $16–$22/hr

    Mercor

    Candidates need native fluency in English and Assamese, strong judgment about language and content accuracy, and careful attention to small errors. Experience in adversarial ML or cybersecurity is preferred.

    ML, Research, Work independently, Communication skills, Adaptability, Cybersecurity

    AI Safety Expert - Adversarial ML

    Toronto, ON
    $16–$22/hr

    Mercor

    Candidates need native fluency in English and Kannada, strong judgment about language accuracy, and a careful eye for subtle errors. Adversarial ML or cybersecurity experience is preferred.

    ML, Research, Communication skills, Adaptability, Cybersecurity, Penetration testing

Locations & environments

Locations

All of CanadaRemote · Hybrid · On-site · Field

Pro tip: add remote jobs to widen your search.

Exclude locations

Workplace type

Company jobs in these results

These are this company’s jobs loaded in your current search. The company may have more openings.