AI / Emerging Tech Security Analyst

Job summary

Analyze and test AI and large language models under adversarial conditions, investigating risks such as prompt injection, data leakage, and model abuse. Assess threats and mitigations, document findings, and help improve AI systems’ safety, resilience, and security.

Job details

About The Role What if your security expertise could directly shape the safety of the AI systems that millions of people rely on every day? We're looking for AI Security Analysts to probe, stress-test, and evaluate frontier AI models — identifying how they can be attacked, manipulated, or misused before those vulnerabilities become real-world problems. This is a fully remote, flexible contract role built for security professionals who are curious about how modern AI systems work — and how they break. Organization: Alignerr Type: Hourly Contract Location: Remote Commitment: 10–40 hours/week What You'll Do Analyze AI and LLM security scenarios to understand how models behave under adversarial or unexpected conditions Investigate and classify cases involving prompt injection, data leakage, model abuse, and system misuse Apply threat modeling frameworks to evaluate real-world impact and likelihood of identified risks Recommend and assess appropriate mitigations to improve AI system resilience Help evaluate and improve AI behavior so it remains safe, reliable, and aligned with security best practices Work independently on task-based assignments at your own pace Who You Are Background in cybersecurity, information security, or a closely related field Strong understanding of modern threat modeling and how it applies to AI and emerging technologies Familiar with adversarial attack surfaces — prompt injection, data poisoning, model extraction, and more Analytically sharp — you approach complex systems methodically and document findings clearly Naturally curious about how AI models are built, deployed, and exploited Self-motivated and reliable when working independently without supervision Nice to Have Hands-on experience with penetration testing, red teaming, or vulnerability research Familiarity with large language models (LLMs) or generative AI systems Background in applied AI, ML security, or adversarial machine learning Experience with OWASP, MITRE ATT&CK, or similar security frameworks Prior work in AI safety, trust and safety, or policy-adjacent security roles Why Join Us Work directly on frontier AI systems alongside leading AI research labs Fully remote and flexible — work when and where it suits you Freelance autonomy with the structure of meaningful, high-impact work Contribute to a mission that matters: keeping the world's most capable AI systems safe and trustworthy Potential for ongoing work and contract extension as new projects launch

What you’ll do

Analyze and test AI and large language models under adversarial conditions, investigating risks such as prompt injection, data leakage, and model abuse. Assess threats and mitigations, document findings, and help improve AI systems’ safety, resilience, and security.

Requirements

Candidates should have a background in cybersecurity or information security, understand threat modeling and AI attack surfaces, and be able to analyze complex systems and document findings clearly. The role also requires curiosity, reliability, and the ability to work independently; experience in penetration testing, red teaming, AI security, or relevant frameworks is an advantage.

Benefits

• Flexible Schedule
• Remote Work
• Potential Contract Extension

Listed skills

• Organization · Preferred
• Reliability · Preferred
• Attention to detail · Preferred
• safety · Preferred
• Machine learning · Preferred
• Supervision · Preferred
• Reliable · Preferred
• Flexible · Preferred

Other relevant skills

Identified from the job description. Confirm important requirements above.

• Cybersecurity
• Information Security
• AI Security
• Threat Modeling
• Prompt Injection Analysis
• Data Poisoning
• Model Extraction
• Penetration Testing
• Red Teaming
• Vulnerability Research
• Large Language Models
• Generative AI
• Machine Learning Security
• Adversarial Machine Learning
• OWASP
• MITRE ATT&CK

Job areas

• Security & Safety
• Technology
• Software
• Science & Research

More jobs from Alignerr