AI / Emerging Tech Security Analyst

Alignerr Corp.; Rio de Janeiro; Remote; BRL 173,000 - 414,000; Part time

Benefits offered by this job

Fully remote

Flexible schedule

Job summary

Alignerr seeks an AI Security Analyst to stress-test frontier AI models, probing for vulnerabilities and validating risk classifications. You’ll help shape how AI systems defend themselves against attack while supporting safe, reliable deployment at scale.

This fully remote hourly contract offers flexible scheduling, with 10–40 hours per week and opportunities for ongoing collaboration as new projects launch.

Qualifications

• Background in cybersecurity or information security.
• Strong understanding of threat modeling for AI systems.
• Familiar with adversarial prompting or AI system abuse vectors.
• Naturally analytical and precise in approach.
• Clear and concise written communicator.

Responsibilities

• Analyze AI and LLM security scenarios to understand behavior under adversarial conditions.
• Review and evaluate prompt injection, data leakage, model abuse, and system misuse cases.
• Classify security issues by impact and likelihood; recommend mitigations.
• Contribute to safer, more reliable AI system behavior and security best practices.
• Work independently on task-based assignments with flexible scheduling.

Skills

Cybersecurity fundamentals

Threat modeling

Adversarial prompts

Analytical mindset

Written communication

Job description

AI / Emerging Tech Security Analyst (AI Training)

About The Role

What if your security expertise could directly shape how the world's most advanced AI systems defend themselves against attack? We're looking for AI Security Analysts to stress-test frontier models — probing for vulnerabilities, classifying risks, and helping ensure that cutting-edge AI remains safe, reliable, and resistant to misuse.

This is a fully remote, flexible contract role built for security professionals who are curious about how modern AI systems can be exploited, manipulated, or pushed beyond their intended boundaries. You'll work on real scenarios with real impact — contributing directly to the safety of AI models being deployed at scale.

• 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
• Review and evaluate cases involving prompt injection, data leakage, model abuse, and system misuse
• Classify security issues by real-world impact and likelihood, and recommend appropriate mitigations
• Help evaluate and improve AI system behavior to ensure it remains safe, reliable, and aligned with security best practices
• Work independently on task-based assignments, fully 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 emerging AI technologies
• Familiar with concepts like adversarial prompting, model exploitation, or AI system abuse vectors
• Naturally analytical and precise — you approach complex systems methodically and think like an attacker
• Curious about how AI models are built, deployed, and where they break down
• Clear and concise written communicator who can document findings with precision

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 application security, API security, or cloud security
• Experience with AI safety, alignment research, or responsible AI practices
• Knowledge of OWASP, MITRE ATT&CK, or similar security frameworks

Why Join Us

• Work directly on frontier AI systems alongside leading 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 critical and fast-moving fields in technology
• Contribute to work that genuinely matters — helping keep powerful AI systems safe at scale
• Potential for ongoing work and contract extension as new projects launch