AI / Emerging Tech Security Analyst

Alignerr Corp.; Deutschland; Remote; EUR 83,000 - 165,000; Full time

Benefits offered by this job

Fully remote

Flexible schedule

Contract / Task-Based

Job summary

Alignerr Corp. is seeking AI Security Analysts to help safeguard frontier AI systems. This fully remote contract role focuses on analyzing vulnerabilities, edge cases, and adversarial scenarios to push AI safety forward.

You will work independently, deliver structured findings, and collaborate with research teams on real-world cases like prompt injection and data leakage.

This flexible, task-based engagement offers 10-40 hours per week and the chance of ongoing work as new projects launch.

Qualifications

• Experience in security disciplines such as threat modeling, pentesting, or vulnerability research.
• Ability to apply security frameworks to AI systems.
• Strong analytical and edge-case thinking for adversarial scenarios.

Responsibilities

• Analyze AI security scenarios and model behavior under adversarial conditions.
• Investigate prompt injection, data leakage, model abuse, and boundary violations.
• Classify issues by impact and likelihood; propose mitigations.
• Evaluate system behavior against security best practices; document findings.
• Contribute expert feedback to improve frontier AI safety and reliability.

Skills

Threat modeling

Penetration testing

Vulnerability research

Security engineering

Analytical thinking

Tools

LLMs

AI APIs

Job description

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 dig into the vulnerabilities, edge cases, and adversarial scenarios that push modern AI beyond its limits - and help make it safer for everyone.

This is a fully remote, flexible contract role built for security professionals who are curious about AI and want to work on problems that genuinely matter. You'll be operating at the intersection of cybersecurity and frontier AI - one of the most consequential spaces in tech right now.

• 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 misuse conditions
• Investigate real-world cases involving prompt injection, data leakage, model abuse, and system boundary violations
• Classify security issues by impact and likelihood, and propose appropriate mitigations
• Evaluate AI system behavior against security best practices and flag risks with clear, structured documentation
• Help improve the safety and reliability of frontier AI systems through expert analysis and feedback

Who You Are

• Experienced in security - whether that’s threat modeling, penetration testing, vulnerability research, or security engineering
• Genuinely curious about how AI systems are built, deployed, and potentially exploited
• Sharp, analytical, and precise - you think in edge cases and adversarial scenarios naturally
• Able to apply traditional security frameworks to emerging AI technologies
• Comfortable working independently and delivering structured, well-reasoned findings

Nice to Have

• Hands-on experience with LLMs, AI APIs, or machine learning systems
• Familiarity with prompt injection, jailbreaking techniques, or AI red-teaming
• Background in application security, threat intelligence, or secure system design
• Prior work in AI safety, trust and safety, or responsible AI research

Why Join Us

• Work directly on frontier AI systems alongside leading research labs and teams
• Fully remote and flexible - structure your work around your life, not the other way around
• Freelance autonomy with the substance of high-impact, technically challenging work
• Be part of a fast-moving field where your contributions have real, lasting consequences for AI safety
• Potential for ongoing work and contract extension as new projects launch