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

Job Overview

Location:

Remote (United States, Brazil). Role:
Red Teamer for Conversational AI. Full-time or part-time contract work. Requires fluent English & Brazilian Portuguese.

• 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, flag systemic risks.
• Apply structure: follow taxonomies, benchmarks, playbooks for consistent testing.
• Document reproducibly: produce reports, datasets, attack cases for customer use.

• Prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• Curious and adversarial, instinctively push systems to breaking points.
• Structured approach: use frameworks or benchmarks, not random hacks.
• Communicative: explain risks to technical and non-technical stakeholders.
• Adaptable: thrive on moving across projects and customers.

• 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.

• Uncover vulnerabilities automated tests miss.
• Deliver reproducible artifacts that strengthen customer AI systems.
• Expand evaluation coverage: more scenarios tested, fewer surprises.
• Build customer trust in AI safety through proactive probing.

Build experience in human data-driven AI red teaming at the frontier of safety. Play a direct role in making AI systems more robust, safe, and trustworthy.

Contract rate aligned with expertise, sensitivity of material, and scope of work. Competitive rates commensurate with experience.