Remote AI Red Team Tester - Creative Safety Evaluator

Alignerr Corp.; Colombia; Presencial; COP 68.894.000 - 183.717.000; A tiempo parcial

Descripción de la vacante

Alignerr is seeking AI Red Team Testers to creatively probe and break AI systems from an adversarial perspective. This remote hourly contract offers 10-40 hours per week and collaboration with AI safety and research teams across diverse AI systems and topics.

No cybersecurity background is required; a curious mind, puzzle-solving skill, and strong English writing are valued traits for this role.

Formación

• Curious thinker who enjoys puzzles and edge cases.
• Able to approach problems from an adversarial angle.
• Systematic and detail-oriented - documents clearly and thoroughly.
• Strong written communication in English.
• Self-motivated and reliable in async, remote work.
• No cybersecurity or AI background required.

Responsabilidades

• Design creative prompts and scenarios to expose AI weaknesses.
• Attempt to elicit incorrect, biased, harmful, or policy-violating outputs from AI models.
• Document every failure with clear, reproducible steps.
• Rate the severity and potential impact of each issue discovered.
• Provide structured, detailed feedback using evaluation frameworks.
• Collaborate asynchronously with AI safety and research teams.
• Work across a range of AI systems, topics, and testing methodologies.

Conocimientos

Curiosity

Puzzle solving

Adversarial thinking

Detail oriented

Written English

Descripción del empleo

Alignerr is seeking AI Red Team Testers to creatively probe and break AI systems from an adversarial perspective. This remote hourly contract offers 10-40 hours per week and collaboration with AI safety and research teams across diverse AI systems and topics.

No cybersecurity background is required; a curious mind, puzzle-solving skill, and strong English writing are valued traits for this role.