**Role & seniority: ** AI Red Team Tester (contract); no specific seniority stated (hourly freelance contributor)

**Stack/tools: ** Not specified; uses AI model interfaces and prompt/conversation testing; documentation of failure modes (tools unspecified)

**Top 3 responsibilities: **

Design adversarial prompts/scenarios to probe AI model weaknesses
Try to elicit incorrect/unsafe/biased/problematic outputs and identify failure modes
Document issues with reproducible steps and assess severity/impact; share findings with safety/research teams
Must-have skills:
- Adversarial mindset; can think “what could go wrong”
- Detail-oriented, systematic troubleshooting and clear documentation
- Strong written communication in structured, actionable formats
- Self-motivated/reliable working independently
- Comfortable working across varied AI models/task types
- Curiosity/creativity and puzzle-solving
Nice-to-haves:
- Creative writing, journalism, research, or critical analysis experience
- Familiarity with AI chatbots/language models as an end user
- Background in philosophy/ethics/psychology/social sciences
- QA or software testing experience
Location & work type: Fully remote; flexible contract, 10–40 hours/week (hourly)

Full Description

About The Role

What if your curiosity, creativity, and knack for thinking outside the box could make AI systems safer for everyone? We're looking for AI Red Team Testers to do exactly that — probe, challenge, and outwit cutting-edge AI models to expose their blind spots before they cause real-world harm.

This is a fully remote, flexible contract role open to anyone who loves puzzles, thinks adversarially, and enjoys finding the cracks in seemingly solid systems. No cybersecurity or technical background required.

Organization: Alignerr

Type: Hourly Contract

Location: Remote

Commitment: 10–40 hours/week

What You'll Do

Design inventive prompts, scenarios, and conversational strategies to probe AI model weaknesses Attempt to elicit incorrect, unsafe, biased, or otherwise problematic outputs from AI systems Document discovered failure modes with clear, reproducible steps so they can be fixed Assess and rate the severity and potential impact of each issue you uncover Collaborate asynchronously with AI safety and research teams to share findings Work across a variety of AI models and task types as new projects arise

Who You Are

A creative, curious thinker who genuinely enjoys puzzles and finding unexpected solutions Comfortable adopting an adversarial mindset — you naturally look for what could go wrong

Detail-oriented and systematic: you don't just find problems, you document them clearly Strong written communicator who can explain findings in structured, actionable formats Self-motivated and reliable — you can work independently without close supervision No background in hacking, cybersecurity, or AI required

Nice to Have

Experience in creative writing, journalism, research, or critical analysis Familiarity with AI chatbots or language models as an end user Background in philosophy, ethics, psychology, or social sciences Prior experience in quality assurance or software testing

Why Join Us

Work on meaningful, high-impact AI safety projects alongside leading research labs Fully remote and flexible — set your own schedule and work from anywhere Freelance autonomy with the satisfaction of structured, purpose-driven work Contribute directly to making AI safer, more reliable, and more trustworthy for people everywhere Potential for ongoing work and contract extension as new projects launch