AI Red Team Tester

Alignerr Corp.; India; Remote; INR 3,302,000 - 7,925,000; Part time

Job summary

Alignerr is seeking AI Red Team Testers to probe cutting-edge AI systems, design adversarial prompts, and document failures to help improve safety. This is a remote, hourly-contract role offering flexible hours and the chance to impact real-world AI safety work.

Ideal candidates enjoy puzzles, think in edge cases, and can communicate findings clearly with research teams across time zones. No cybersecurity background required.

Qualifications

• A naturally curious thinker who enjoys poking at systems to see how they break (edge-case thinking).
• Detail-oriented, methodical in documenting findings.
• Strong written communicator able to explain complex observations.

Responsibilities

• Design creative, adversarial prompts and scenarios to expose AI weaknesses.
• Attempt to elicit incorrect, unsafe, biased, or harmful outputs from AI models.
• Document every failure mode in detail, including clear reproduction steps.
• Rate the severity and potential impact of issues you discover.
• Provide structured, actionable feedback that helps research teams improve AI safety.
• Collaborate asynchronously with safety and research teams across time zones.

Job description

About The Role

What if your curiosity and creativity could make AI safer for everyone? We're looking for AI Red Team Testers to go head-to-head with cutting-edge AI systems — probing, prodding, and stress‑testing them to uncover weaknesses before they cause real-world harm.

This isn't a traditional tech role. It's a thinking role. If you enjoy puzzles, love finding loopholes, and think in edge cases, this is your opportunity to contribute to some of the most important AI safety work happening right now — fully remote and on your own schedule.

• Organization: Alignerr
• Type: Hourly Contract
• Location: Remote
• Commitment: 10–40 hours/week

What You'll Do

• Design creative, adversarial prompts and scenarios to expose AI weaknesses
• Attempt to elicit incorrect, unsafe, biased, or harmful outputs from AI models
• Document every failure mode in detail, including clear reproduction steps
• Rate the severity and potential impact of issues you discover
• Provide structured, actionable feedback that helps research teams improve AI safety
• Collaborate asynchronously with safety and research teams across time zones

Who You Are

• A naturally curious thinker who enjoys poking at systems to see how they break
• Comfortable thinking adversarially — you look for what could go wrong, not just what goes right
• Detail-oriented and methodical in how you document and communicate findings
• Strong written communicator who can clearly explain complex observations
• Self-motivated and reliable working independently in a remote environment
• No hacking, cybersecurity, or AI background required — just sharp thinking and creativity

Nice to Have

• Experience in writing, critical analysis, journalism, or quality assurance
• Familiarity with AI tools or chatbots as an end user
• Background in ethics, psychology, or social science — useful for spotting bias and nuanced failures
• Prior experience in testing, research, or adversarial thinking of any kind

Why Join Us

• Work on meaningful AI safety projects alongside leading research labs
• Fully remote and flexible — work when and where it suits you
• Freelance autonomy with the structure of purposeful, impactful work
• Engage with some of the most fascinating and consequential technology being built today
• Potential for ongoing work and contract extension as new projects launch