AI Security Testing Analyst

Alignerr; United States; Remote; USD 83,000 - 138,000; Full time

Job summary

Alignerr is seeking security-minded professionals to stress-test and probe AI systems from a remote location. You will perform red-teaming, craft adversarial prompts, and evaluate AI outputs for safety and policy compliance. This role emphasizes independent work, asynchronous collaboration, and staying ahead of evolving AI security threats.

The position is hourly, remote, with 10–40 hours per week. Prior experience in infosec, AI safety research, or open-source AI platforms is a plus, and there

Qualifications

• Strong cybersecurity foundation in threat modeling or pentesting.
• Experience with AI/ML systems, LLMs or prompt engineering.
• Creative, analytical mindset and edge-case focus.
• Excellent written communication and documentation.
• Self-directed, asynchronous work style.
• Familiarity with open-source AI platforms is a plus.
• InfoSec or AI safety research background is a bonus

Responsibilities

• Conduct red-teaming exercises to uncover security weaknesses in live AI systems.
• Craft adversarial prompts and edge-case scenarios to test and break model guardrails.
• Evaluate AI outputs for safety issues, bias, and policy compliance.
• Document vulnerabilities, exploits, and unexpected behaviors in reports.
• Collaborate asynchronously with engineering teams to suggest mitigations and improvements.
• Stay updated on emerging AI security threats and jailbreak techniques.
• Help define security evaluation rubrics and testing protocols

Skills

Threat modeling

Penetration testing

Vulnerability assessment

AI/ML systems

LLMs

Prompt engineering

Independent work

Asynchronous communication

Tools

Open-source AI platforms

Job description

About The Role

What if your job was to break things on purpose? We're looking for security-minded professionals to stress-test, probe, and challenge AI systems — finding the cracks before bad actors do. Your work will directly shape the safety and reliability of AI products used by millions of people worldwide.

• Organization: Alignerr


• Type: Hourly Contract


• Location: Remote


• Commitment: 10–40 hours/week

What You'll Do

• Conduct red-teaming exercises to uncover security weaknesses in live AI systems


• Craft adversarial prompts and edge-case scenarios designed to test — and break — model guardrails


• Evaluate AI outputs for safety issues, bias, and policy compliance


• Document vulnerabilities, exploits, and unexpected behaviors in clear, structured reports


• Collaborate asynchronously with engineering teams to recommend mitigations and improvements


• Stay sharp on emerging AI security threats, jailbreak techniques, and evolving best practices


• Help define and refine security evaluation rubrics and testing protocols

Who You Are

• Strong grasp of cybersecurity concepts — threat modeling, penetration testing, or vulnerability assessment


• Hands-on experience with AI/ML systems, large language models (LLMs), or prompt engineering


• Creative and analytical mindset — you enjoy finding the edge cases others miss


• Excellent written communication and documentation skills


• Self-directed and comfortable working independently on asynchronous, task-based assignments


• Familiarity with open-source AI platforms is a plus


• Background in infosec, ethical hacking, or AI safety research is a bonus — not a requirement

Why This Role Stands Out

• Real impact: Your findings directly improve AI safety for products used at scale


• Cutting-edge work: Operate at the intersection of cybersecurity and AI — one of the most in-demand skill sets in tech


• Full flexibility: Remote-first, async-friendly, and built around your schedule


• Build your expertise: Deepen your knowledge in AI red-teaming, a rapidly growing and highly valued field


• Grow with us: Strong performers have opportunities for expanded scope and ongoing contract work