AI Red-Teamer Adversarial AI Testing

About the Role

hackajob is collaborating with Mercor to connect them with exceptional tech professionals for this role. In this position, you will red team conversational AI models and agents, probing them with adversarial inputs to surface vulnerabilities and generate valuable data that improves AI safety.

Location & Work Arrangement

This is a remote role, limited to candidates in the USA and Europe.

Key Responsibilities

• Red team AI models: jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag risks.
• Follow frameworks: adhere to taxonomies, benchmarks, and playbooks for consistent testing.
• Produce detailed documentation: reports, datasets, and attack cases for customer actions.

Who You Are

You have prior red teaming or cybersecurity experience with adversarial work. You are curious, adversarial, structured, communicative, and adaptable. Experience in adversarial ML, penetration testing, or socio-technical risk analysis is a plus.

Key Skills/Competency

• Red Teaming
• Adversarial Testing
• Cybersecurity
• ML Adversaries
• Risk Analysis
• Data Annotation
• Documentation
• Benchmarking
• Prompt Injection
• Cross-functional Communication