AI Red-Teamer — Adversarial AI Testing (Advanced); English & Hebrew (Train AI Models Part Time!) jobs in United States
cer-icon
Apply on Employer Site
company-logo

hackajob · 1 day ago

AI Red-Teamer — Adversarial AI Testing (Advanced); English & Hebrew (Train AI Models Part Time!)

positionUnited States
timePart-time, Contract
remoteRemote
seniorityMid, Senior Level

hackajob is collaborating with Mercor to connect them with exceptional tech professionals for this role. The AI Red-Teamer will work on probing AI models with adversarial inputs, identifying vulnerabilities, and generating data to enhance AI safety for customers.

Artificial Intelligence (AI)Generative AIHuman ResourcesRecruitingSoftware

Responsibilities

Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation
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

Qualification

Red teaming experienceAdversarial MLCybersecurityStructured testingFluent in EnglishFluent in HebrewCommunicativeCreative probingAdaptable

Required

Fluent Language Skills Required: English & Hebrew. Native-level fluency in English and Hebrew is required for this position
You bring prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing)
You're curious and adversarial: you instinctively push systems to breaking points
You're structured: you use frameworks or benchmarks, not just random hacks
You're communicative: you explain risks clearly to technical and non-technical stakeholders
You're adaptable: thrive on moving across projects 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

Company

hackajob

twittertwittertwitter
company-logo
The AI-native tech hiring platform trusted by enterprises, scale-ups, and 1M+ tech professionals worldwide.
dateFounded in 2014
location
London, England, GBR
people-size51-200 employees
web-link
http://www.hackajob.com

Funding

Current Stage
Growth Stage
Total Funding
$33M
Key Investors
Volition CapitalDowning VenturesTechstars
2023-05-03Series B· $25M
2018-10-25Series A· $6.7M
2017-03-31Seed· $0.58M

Leadership Team

leader-logo
Mark Chaffey
CEO
linkedin
leader-logo
Phil Kell
VP - Marketplace
linkedin

Recent News

AIM Group
Tech-focused hiring site HackAJob launches dedicated AI voice agents
2025-10-23
AIM Group
Application tsunami, fake profiles drive verification race among job sites
2025-09-26
PR Newswire UK
hackajob launches AI agents to make recruitment more human again
2025-09-12
Company data provided by crunchbase