Remote AI Security Red Team Analyst

Alignerr Corp.; Greater London; Remote; GBP 83,000 - 124,000; Part time

Job summary

Alignerr is seeking security-minded professionals to probe, stress-test, and red-team AI models on a remote hourly contract. You will surface weaknesses before they impact users and contribute to safer AI products used worldwide.

The role offers flexible hours (10–40 per week) and practical impact in a fast-evolving field. You will conduct red-teaming exercises, design adversarial prompts, assess safety and bias, and document findings for engineering teams.

Qualifications

• Strong foundation in cybersecurity concepts such as threat modelling, pentesting, or vulnerability research.
• Hands-on experience with AI/ML systems, LLMs, or prompt engineering.
• Creative adversarial mindset with reporting skills.
• Self-directed, asynchronous work style with clear communication.
• Familiarity with open-source AI platforms is a plus.

Responsibilities

• Conduct red-teaming to surface AI security weaknesses.
• Design adversarial prompts and edge-case tests for guardrails.
• Evaluate AI outputs for safety and bias.
• Document vulnerabilities and reports clearly.
• Collaborate with engineers on mitigations.

Skills

Threat modeling

Penetration testing

Vulnerability research

AI/ML systems

Prompt engineering

Technical writing

Async work

Tools

Open-source AI platforms

Job description

Alignerr is seeking security-minded professionals to probe, stress-test, and red-team AI models on a remote hourly contract. You will surface weaknesses before they impact users and contribute to safer AI products used worldwide.

The role offers flexible hours (10–40 per week) and practical impact in a fast-evolving field. You will conduct red-teaming exercises, design adversarial prompts, assess safety and bias, and document findings for engineering teams.