AI Safety Red Team Tester — Remote, Flexible Hours

Alignerr Corp.; Philippines; Remote; PHP 1,294,000 - 3,450,000; Full time

Job summary

Alignerr Corp. is seeking AI Red Team Testers to probe cutting-edge AI systems, crafting prompts and uncovering failure modes that engineers must fix. This remote, hourly-contract role fits 10–40 hours per week and is open to talents worldwide.

You'll design adversarial prompts, document failures with reproducible steps, assess severity, and deliver structured reports to safety and research teams. Strong written communication and independent work are essential.

Qualifications

• Design adversarial prompts to expose AI weaknesses.
• Document failures with clear, reproducible steps.
• Assess and rate severity and potential impact of issues found.

Responsibilities

• Design creative prompts and scenarios to probe AI weaknesses.
• Attempt to elicit incorrect, unsafe, or biased outputs from AI models.
• Document every failure mode with reproducible steps.
• Assess severity and potential impact of issues found.
• Provide structured, detailed reports for safety and research teams.
• Collaborate asynchronously with AI safety and research teams across the globe.

Skills

Adversarial prompt design

Prompt engineering

Structured reporting

Independent work

Tools

AI safety tools

Job description

Alignerr Corp. is seeking AI Red Team Testers to probe cutting-edge AI systems, crafting prompts and uncovering failure modes that engineers must fix. This remote, hourly-contract role fits 10–40 hours per week and is open to talents worldwide.

You'll design adversarial prompts, document failures with reproducible steps, assess severity, and deliver structured reports to safety and research teams. Strong written communication and independent work are essential.