Adversarial AI Testing (Remote)

Freelancing; Malaysia; Hybrid; MYR 83,000 - 165,000; Full time

Job summary

A technology consulting firm based in Malaysia is seeking a human data expert to red team AI models, probing them against adversarial inputs. The successful candidate will generate high-quality human data, classify vulnerabilities, and document findings to enhance AI safety. A prior background in adversarial work, strong communication skills, and adaptability are essential for this role, as you'll navigate various sensitive projects with clear guidelines to ensure safety and effectiveness.

Qualifications

• Experience in adversarial work related to AI or cybersecurity.
• Ability to explain risks and methodologies to diverse audiences.
• Experience with socio-technical risk analysis in AI contexts.

Responsibilities

• Red team conversational AI models and agents using various techniques.
• Generate high-quality human data by annotating failures and vulnerabilities.
• Follow structured methodologies to ensure consistency in testing.
• Document processes and findings in clear reports and datasets.

Skills

Prior red teaming experience

Curiosity and adversarial mindset

Structured approach using benchmarks

Effective communication skills

Adaptability

Job description

We are assembling a human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate the red team data that makes AI safer for our customers.

This project involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors. All work is text-based, and participation in higher-sensitivity projects is optional and supported by clear guidelines and wellness resources. Before being exposed to any content, the topics will be clearly communicated.

What You’ll Do

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

Who You Are

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

Nice-to-Have Specialties

Socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing

Creative probing: psychology, acting, writing for unconventional adversarial thinking

What Success Looks Like

You uncover vulnerabilities automated tests miss

You deliver reproducible artifacts that strengthen customer AI systems

Mercor customers trust the safety of their AI because you’ve already probed it like an adversary