AI Red Team Tester

Alignerr; Philippines; Remote; PHP 276,000 - 551,000; Full time

Benefits offered by this job

Remote work

Flexible hours

Freelance contract

Job summary

Alignerr Corp. is seeking AI Red Team Testers to challenge cutting-edge AI systems with creative prompts, probing for blind spots and failure modes in a fully remote hourly-contract role.

You'll design adversarial prompts, document failures with reproducible steps, and report findings to safety and research teams. No cybersecurity background required—just curious, precise thinkers who work well async.

Qualifications

• Strong curiosity and problem-solving mindset.
• Ability to document findings clearly and reproducibly.
• Comfort with asynchronous, remote collaboration.

Responsibilities

• Design creative adversarial prompts to expose AI weaknesses.
• Elicit unsafe or biased outputs from AI models and document failures.
• Assess severity and impact of issues and report findings with steps to reproduce.
• Provide structured reports for safety and research teams to act on.
• Collaborate asynchronously with global AI safety teams.

Skills

Adversarial thinking

Prompt design

Critical thinking

Written communication

Job description

About The Role

What if your curiosity, creativity, and knack for finding loopholes could make AI safer for everyone? We're looking for AI Red Team Testers to put cutting-edge AI systems to the test — crafting clever prompts, probing for blind spots, and uncovering the failure modes that engineers need to fix.

About The Role

What if your curiosity, creativity, and knack for finding loopholes could make AI safer for everyone? We're looking for AI Red Team Testers to put cutting-edge AI systems to the test — crafting clever prompts, probing for blind spots, and uncovering the failure modes that engineers need to fix.

This is a fully remote, flexible contract role open to anyone with sharp critical thinking and a talent for thinking outside the box. No cybersecurity or hacking background required — just a curious mind and a love of intellectual challenge.

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

What You'll Do

• Design creative, adversarial prompts and scenarios specifically aimed at exposing AI weaknesses
• Attempt to elicit incorrect, unsafe, biased, or otherwise problematic outputs from AI models
• Document every failure mode you discover with clear, reproducible steps
• Assess and rate the severity and potential impact of issues found
• Provide structured, detailed reports that safety and research teams can act on
• Collaborate asynchronously with AI safety and research teams across the globe

Who You Are

• Naturally curious — you enjoy puzzles, edge cases, and thinking adversarially
• Creative and systematic: you can approach problems from unexpected angles while staying methodical
• A clear, precise written communicator who can document findings in a structured way
• Detail-oriented and consistent across assignments
• Comfortable working independently in a remote, async environment
• No background in hacking, cybersecurity, or AI required

Nice to Have

• Experience in writing, creative fiction, philosophy, or debate — fields that train unconventional thinking
• Familiarity with AI tools or chatbots as an end user
• Background in QA, research, critical analysis, or investigative work
• Interest in AI ethics, safety, or alignment

Why Join Us

• Work on meaningful, cutting-edge AI safety projects alongside leading research labs
• Fully remote and flexible — work when and where it suits you
• Freelance autonomy with the structure of task-based, intellectually stimulating work
• Contribute directly to making AI systems safer and more reliable for people everywhere
• Variety in every project — no two assignments are the same
• Potential for ongoing work and contract extension as new projects launch