AI / Emerging Tech Security Analyst

Alignerr; United States; Remote; AUD 83,000 - 165,000; Full time

Job summary

Alignerr is seeking AI Security Analysts to probe frontier AI models, identifying vulnerabilities and misuse scenarios before real-world problems arise.

This fully remote contract role offers 10–40 hours per week and asynchronous work. Ideal candidates have a cybersecurity background, threat modeling experience, and familiarity with AI/LLM security concepts.

Qualifications

• Bachelor's or equivalent in cybersecurity or related field.
• Strong analytical skills and attention to detail.
• Experience with AI/LLM security concepts.
• Ability to work independently with minimal oversight.
• Familiarity with threat modeling and risk assessment.

Responsibilities

• Analyze AI and LLM security scenarios to test model behavior under adversarial or edge-case conditions.
• Review prompt injection attempts, data leakage risks, model abuse patterns, and system misuse cases.
• Classify vulnerabilities and recommend mitigations based on impact and likelihood.
• Assess AI system behavior and identify deviations from safe, reliable operation.
• Present findings in structured, actionable formats for stakeholders.
• Work independently and asynchronously—fully on your own schedule.

Skills

Cybersecurity

Threat modeling

AI/LLM security

Analytical thinking

Independent work

Education

Cybersecurity background

Tools

AI APIs

ML pipelines

Job description

About The Role

What if your security expertise could directly shape the safety of the most powerful AI systems ever built? We're looking for AI Security Analysts to probe, test, and evaluate frontier AI models — uncovering vulnerabilities, adversarial attack vectors, and misuse scenarios before they become real-world problems.

This is a fully remote, flexible contract role built for security professionals who are curious about AI and want to work at the cutting edge of one of the most consequential fields in tech. You'll work directly with realistic scenarios on live AI systems — not simulations, not theory.

• Organization: Alignerr
• Type: Contract / Task-Based
• Location: Remote
• Commitment: 10–40 hours/week

What You'll Do

• Analyze AI and LLM security scenarios to understand how models behave under adversarial, unexpected, or edge-case conditions
• Review and evaluate prompt injection attempts, data leakage risks, model abuse patterns, and system misuse cases
• Classify security vulnerabilities and recommend appropriate mitigations based on real-world impact and likelihood
• Assess AI system behavior and identify where outputs deviate from safe, reliable, and intended operation
• Help improve model robustness by surfacing findings in structured, actionable formats
• Work independently and asynchronously — fully on your own schedule

Who You Are

• Background in cybersecurity, information security, or a related security discipline
• Strong understanding of modern threat modeling, applied to AI or software systems
• Familiar with concepts like prompt injection, adversarial inputs, privilege escalation, or data exfiltration in the context of AI/LLM systems
• Analytical and precise — you think systematically when evaluating complex systems and potential failure modes
• Naturally curious about how things break, not just how they work
• Comfortable working independently with minimal oversight

Nice to Have

• Hands-on experience with LLMs, AI APIs, or ML pipelines
• Background in red teaming, penetration testing, or security research
• Familiarity with AI safety concepts, model alignment, or responsible AI practices
• Experience evaluating or auditing software systems for security compliance