Remote AI Security Tester — Stress-Test & Harden AI Systems

Alignerr Corp.; New York (NY); Remote; USD 83,000 - 165,000; Part time

Job summary

Alignerr is seeking security-minded professionals to stress-test and harden AI systems by identifying vulnerabilities before bad actors do. You will conduct red-team exercises, craft adversarial prompts, and deliver expert feedback shaping safety and reliability for AI products used worldwide.

The role involves evaluating AI outputs for safety risks, bias, and policy compliance, documenting findings, and collaborating with engineering teams to implement mitigations.

Qualifications

• Solid understanding of cybersecurity concepts, threat modeling, or penetration testing.
• Hands-on with AI/ML systems, large language models, or prompt engineering.
• Creative, analytical thinker who enjoys finding cracks in complex systems.
• Writes clearly and documents findings in an organized way.
• Comfortable working independently on task-based, asynchronous assignments.
• Familiarity with open-source AI platforms.
• Background in infosec, ethical hacking, or AI safety research is a bonus.

Responsibilities

• Conduct red-teaming exercises to identify security weaknesses and failure modes in AI systems.
• Craft adversarial prompts and edge-case scenarios designed to probe and stress-test model guardrails.
• Evaluate AI outputs for safety risks, bias, and policy compliance.
• Document vulnerabilities, exploits, and unexpected behaviors in clear, structured reports.
• Collaborate with engineering teams to recommend practical mitigations and improvements.
• Stay current on emerging AI security threats, jailbreak techniques, and evolving best practices.
• Help define and refine security evaluation rubrics and testing protocols.

Skills

Cybersecurity concepts

Threat modeling

Penetration testing

AI/ML experience

Prompt engineering

Analytical thinking

Documentation

Independent work

Open-source AI familiarity

AI safety background

Job description

Alignerr is seeking security-minded professionals to stress-test and harden AI systems by identifying vulnerabilities before bad actors do. You will conduct red-team exercises, craft adversarial prompts, and deliver expert feedback shaping safety and reliability for AI products used worldwide.

The role involves evaluating AI outputs for safety risks, bias, and policy compliance, documenting findings, and collaborating with engineering teams to implement mitigations.