AI Red-Teamer — Adversarial AI Testing (Advanced); English & Brazilian Portuguese

Parailabs; Brazil (IN); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Parailabs is seeking security-focused professionals to conduct advanced adversarial testing on conversational AI systems. You will design datasets to improve reasoning and function calling accuracy, and assess personalization across cultures, including Japanese user behavior.

You will participate in a structured interview process to shape benchmarks that measure agent performance in enterprise security tasks, working with skilled defenders over several weeks.

Qualifications

Responsibilities

• Conduct advanced adversarial testing on conversational AI systems to uncover vulnerabilities.
• Design and craft multi-turn conversational datasets to improve AI agent reasoning, function calling accuracy, and real-world interaction capabilities.
• Evaluate personalization quality in AI systems using cultural and contextual understanding of Japanese user behavior.
• Working cyber defenders join two to three paid one-hour interviews over about four weeks to shape a benchmark measuring how well AI agents perform real enterprise security work.

Skills

AI Red Teaming

Cybersecurity

Critical Thinking

English (Native)

Portuguese (Brazilian)

Job description

Conduct advanced adversarial testing on conversational AI systems to uncover vulnerabilities.

Mercor hasn't published a full description for this project outside itsapplication flow. Pay, commitment, and eligibility are listed above; the completebrief appears once you open the application.

Skills

AI Red Teaming Cybersecurity Critical Thinking English (Native) Brazilian Portuguese (Native)

Design and craft multi-turn conversational datasets to improve AI agent reasoning, function calling accuracy, and real-world interaction capabilities.

Evaluate personalization quality in AI systems using cultural and contextual understanding of Japanese user behavior.

Working cyber defenders join two to three paid one-hour interviews over about four weeks to shape a benchmark measuring how well AI agents perform real enterprise security work.