Flag job

Report

AI Red-Teamer

Salary

$54k - $111k

Min Experience

0 years

Location

India

JobType

part-time

About the job

Info This job is sourced from a job board

About the role

Job Title:

AI Red-Teamer – Adversarial AI Testing (Advanced, Contract, Remote)



About the Role

:Our organization is building a specialized team of AI Red-Teamers to proactively identify vulnerabilities in AI systems. As an AI Red-Teamer, you will use adversarial inputs, creative probing, and structured evaluation to surface potential risks and improve the safety, robustness, and trustworthiness of AI models. This fully remote role offers the opportunity to work across high-impact projects, exploring the frontiers of AI security and ethical safeguards


.
Key Responsibilitie

  • s:Conduct adversarial testing on AI models and agents, including jailbreaks, prompt injections, and misuse case
  • s.Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risk
  • s.Apply structured frameworks, taxonomies, benchmarks, and playbooks to ensure consistent testin
  • g.Produce reproducible reports, datasets, and attack cases that can be acted upon by customers and internal team
  • s.Support multiple projects and customers, ranging from LLM jailbreaks to socio-technical abuse testin


g.
Qualifications / Skills Requir

  • ed:Prior experience in AI red-teaming, cybersecurity, or adversarial testi
  • ng.Strong analytical and adversarial mindset; instinctively probe systems to find weakness
  • es.Structured approach to testing, using frameworks and benchmar
  • ks.Excellent communication skills to clearly convey risks to both technical and non-technical stakeholde
  • rs.Adaptable and comfortable moving across multiple projects and domai


ns.
Preferred Qualificati

  • ons:Adversarial ML expertise: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extract
  • ion.Cybersecurity experience: penetration testing, exploit development, reverse engineer
  • ing.Socio-technical risk analysis: harassment/disinformation probing, abuse evaluat
  • ion.Creative probing skills: psychology, acting, or writing for unconventional adversarial scenar


ios.
Work Loca

tion:Remote – US-friendly time zones (restricted to US, UK, Can


ada).
Salary

Range:$54–$111 per hour (contra


ctor).
Additional D

  • etails:Full-time or part-time engagement, flexible across pr
  • ojects.Participation in higher-sensitivity projects is optional and supported with guidelines and wellness res
  • ources.Play a direct role in making AI systems safer and more reliable for cus


tomers.

Skills

adversarial ml
cybersecurity
socio-technical risk analysis
creative probing