Remote AI Safety Red Team Tester

Alignerr Corp.; United States; Remote; GBP 34,000 - 83,000; Full time

Benefits offered by this job

Fully remote

Flexible schedule

Contract extension potential

Job summary

Alignerr is seeking AI Red Team Testers to challenge AI models and uncover unsafe outputs. This fully remote, hourly contracting role invites curious, critical thinkers to work 10–40 hours per week and help build a safer AI ecosystem.

Responsibilities include designing adversarial prompts, documenting all failure modes with reproducible steps, and collaborating with researchers worldwide to provide actionable feedback. Remote, contract-based engagement with potential extensions.

Qualifications

• What you will do requires curiosity, creativity, and a systematic approach.
• Strong written communication to clearly describe issues and steps.

Responsibilities

• Design prompts, scenarios and strategies to expose AI weaknesses
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs
• Document failures with clear, reproducible steps
• Rate severity and impact of issues found
• Provide structured feedback to safety and research teams
• Collaborate asynchronously with a global team

Skills

Adversarial thinking

Prompt design

Documentation

Communication

Job description

Alignerr is seeking AI Red Team Testers to challenge AI models and uncover unsafe outputs. This fully remote, hourly contracting role invites curious, critical thinkers to work 10–40 hours per week and help build a safer AI ecosystem.

Responsibilities include designing adversarial prompts, documenting all failure modes with reproducible steps, and collaborating with researchers worldwide to provide actionable feedback. Remote, contract-based engagement with potential extensions.