AI Red Team Tester

Alignerr Corp.; Germany; Remote; EUR 44,000 - 88,000; Full time

Job summary

Alignerr is seeking AI Red Team Testers to challenge cutting-edge AI systems in a remote hourly contract. You will craft adversarial prompts, probe models for weaknesses, and document failures with clear steps to help safety teams improve AI behavior.

Ideal candidates think creatively, stay systematic, and communicate issues precisely. This role offers flexible, async collaboration with global safety engineers and researchers.

Qualifications

• Curiosity and critical thinking to identify edge cases.
• Able to think adversarially and anticipate misuse.
• Detail-oriented with thorough documentation of findings.
• Strong written communication and ability to work remotely async.

Responsibilities

• Design creative, adversarial prompts and scenarios specifically crafted to expose AI weaknesses.
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI models.
• Document every failure mode with clear, reproducible steps.
• Rate the severity and potential impact of each issue uncovered.
• Provide structured, detailed feedback for AI safety and research teams.
• Collaborate asynchronously with safety engineers and researchers across global teams.

Skills

Curiosity

Adversarial thinking

Detail-oriented

Written communication

Self-motivation

Job description

About The Role

What if your curiosity and creative thinking 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 pushing them to their limits to uncover weaknesses before they cause real-world harm.

About The Role

What if your curiosity and creative thinking 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 pushing them to their limits to uncover weaknesses before they cause real-world harm. This is your chance to play the role of the adversary — crafting clever scenarios, testing boundaries, and thinking like someone trying to break the rules. No cybersecurity or hacking background required. If you love puzzles, think critically, and enjoy finding the crack in the armor, this role was made for you.

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

What You'll Do

• Design creative, adversarial prompts and scenarios specifically crafted to expose AI weaknesses
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI models
• Document every failure mode you discover with clear, reproducible steps
• Rate the severity and potential impact of each issue uncovered
• Provide structured, detailed feedback that AI safety and research teams can act on
• Collaborate asynchronously with safety engineers and researchers across global teams

Who You Are

• A naturally curious thinker who enjoys breaking things down and finding edge cases
• Comfortable thinking adversarially — you can anticipate how systems might be misused
• Detail-oriented and systematic — you document findings clearly and thoroughly
• Strong written communicator who can articulate issues with precision
• Self-motivated and reliable working independently in a remote, async environment
• No hacking, cybersecurity, or AI background required

Nice to Have

• Experience with creative writing, critical analysis, or structured problem-solving
• Familiarity with AI chatbots or language models as an end user
• Background in ethics, philosophy, policy, psychology, or related fields
• Prior experience in quality assurance, research, or content evaluation

Why Join Us

• Work on meaningful AI safety projects alongside leading research labs
• Fully remote and flexible — set your own schedule and work from anywhere
• Freelance autonomy with consistent, task-based work that keeps things interesting
• Contribute directly to the safety and integrity of AI systems used by millions
• Exposure to cutting-edge AI development at the frontier of the field
• Potential for ongoing work and contract extension as new projects launch