AI Red Team Tester

Alignerr; España; Presencial; EUR 28.000 - 83.000; A tiempo parcial

Ventajas ofrecidas por este puesto de trabajo

Fully remote

Flexible schedule

Freelance autonomy

Ongoing contract potential

Descripción de la vacante

Alignerr is seeking AI Red Team Testers to probe, prod, and challenge AI systems from a remote, freelance position. You will craft prompts to reveal weaknesses, document failure modes with clear steps, and rate the severity of issues to inform safety research.

This flexible, async role requires curiosity, thorough reporting, and reliable self-motivation. No security background is required; prior QA, writing, or critical analysis experience is helpful.

Formación

• Curiosity and ability to craft tests to expose AI weaknesses.
• Strong written communication to document failures clearly.
• Comfort with async remote collaboration.
• No cybersecurity background required.

Responsabilidades

• Design imaginative prompts to expose AI weaknesses.
• Elicit unsafe or biased outputs from AI models.
• Document failure modes with reproducible steps.
• Rate severity and impact of identified issues.
• Prepare detailed reports for AI safety researchers.
• Collaborate with safety engineers and researchers across the globe.

Conocimientos

Curiosity

Creative thinking

Adversarial thinking

Detail-oriented

Written communication

Independent work

Async collaboration

Herramientas

LLMs (large language models)

QA testing tools

Descripción del empleo

About The Role

What if your curiosity and creative thinking could make AI safer for millions of people? We're looking for AI Red Team Testers to do exactly that — probing, prodding, and challenging AI systems to uncover their blind spots before they cause real harm. This isn't a typical testing role. You'll think like an adversary, craft clever prompts, and push AI models to their limits. Your findings will feed directly into safety research at the forefront of AI development. No security background required — just a sharp, inquisitive mind and a knack for finding things that don't belong.

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

What You'll Do

• Design imaginative prompts and scenarios specifically aimed at exposing 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 identified issues
• Contribute structured, detailed reports that inform AI safety and research teams
• Collaborate asynchronously with safety engineers and researchers across the globe

Who You Are

• A naturally curious, creative thinker who enjoys puzzles, edge cases, and poking holes in things
• Comfortable thinking adversarially — you instinctively look for what could go wrong
• Systematic and detail-oriented in how you document and communicate findings
• Strong written communicator who can clearly explain complex failure scenarios
• Self-motivated and reliable working independently in an async environment
• No hacking, cybersecurity, or AI background required

Nice to Have

• Experience in creative writing, debate, philosophy, or critical analysis
• Familiarity with large language models or AI chatbots as an everyday user
• Background in QA testing, research, journalism, or logic-based fields
• Interest in AI ethics, safety, or responsible AI development

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 structured, engaging task-based work
• Contribute to responsible AI development that has a real impact on how AI systems behave in the world
• Potential for ongoing work and contract extension as new projects launch