AI / Emerging Tech Security Analyst

Alignerr Corp.; Cape Town; Remote; ZAR 228,000 - 911,000; Part time

Benefits offered by this job

Fully remote

Flexible schedule

Contract-based

Job summary

Alignerr is seeking AI Security Analysts for a fully remote hourly contract role. You will probe frontier AI models, stress-test vulnerabilities, and identify misuse vectors before they become real-world problems.

The engagement offers 10–40 hours per week with flexible scheduling for security professionals curious about AI. You will analyze security scenarios, investigate prompt injection risks, and classify issues by impact and likelihood to propose mitigations.

Qualifications

• Background in cybersecurity, information security, or a closely related technical field.
• Strong understanding of modern threat modeling principles applied to software or emerging technology systems.
• Familiar with AI or LLM systems — how they're built, deployed, and where they break.

Responsibilities

• Analyze AI and LLM security scenarios to understand model behavior under adversarial conditions.
• Investigate prompt injection attacks, data leakage risks, model abuse patterns, and system misuse cases.
• Classify security issues by real-world impact and likelihood, and recommend mitigations.

Skills

Cybersecurity

Threat modeling

AI safety

Analytical thinking

Tools

STRIDE framework

MITRE ATLAS

Job description

About The Role

What if your security expertise could directly shape how the world's most powerful AI systems defend themselves against attack? We're looking for AI Security Analysts to probe, evaluate, and stress-test frontier AI models — identifying the vulnerabilities, misuse vectors, and adversarial risks that matter most 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 on the cutting edge of both fields.

• 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 prompt injection attacks, data leakage risks, model abuse patterns, and system misuse cases
• Classify security issues by real-world impact and likelihood, and recommend appropriate mitigations
• Evaluate AI system behavior against security best practices and help improve model safety and reliability
• Work through realistic, scenario-based assignments independently on your own schedule

Who You Are

• Background in cybersecurity, information security, or a closely related technical field
• Strong understanding of modern threat modeling principles applied to software or emerging technology systems
• Familiar with AI or LLM systems — how they're built, deployed, and where they break
• Analytical and precise — you think in attack surfaces, failure modes, and risk likelihood
• Naturally curious about how complex systems behave when pushed beyond their intended limits
• Comfortable working independently on structured, task-based assignments

Nice to Have

• Hands‑on experience with red teaming, penetration testing, or adversarial AI research
• Familiarity with prompt injection, jailbreaking, or LLM‑specific attack techniques
• Background in AI safety, responsible AI, or ML security research
• Experience with threat modeling frameworks (STRIDE, MITRE ATLAS, etc.)
• Prior work in cloud security, application security, or API security

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
• Be at the forefront of one of the most consequential challenges in modern technology
• Potential for ongoing work and contract extension as new projects launch