AI / Emerging Tech Security Analyst
Alignerr Corp. · Spain ·
COMPENSATION
€•• – ••k
Listed on WeAreDevelopers
- Fully remote (EU)
- Hourly contract
- Flexible hours
- AI security focus
- Adversarial testing
Join Alignerr as an AI Security Analyst to help ensure cutting-edge AI systems remain safe and resistant to misuse. You will analyze realistic adversarial scenarios, uncover vulnerabilities in large language models, and recommend mitigations based on real-world impact.
This position offers complete autonomy with task-based assignments that fit your schedule. It is ideal for security professionals curious about how modern AI systems can be exploited and how to defend them.
What you'll do
- Analyze AI and LLM security scenarios under adversarial conditions
- Review cases involving prompt injection, data leakage, and model abuse
- Classify security issues and recommend appropriate mitigations
- Apply threat modeling frameworks to emerging AI technologies
- Evaluate and improve AI system behavior for safety and alignment
- Work independently on asynchronous, task-based assignments
What you'll need
- Background in cybersecurity or information security
- Strong understanding of security threat modeling for software
- Ability to notice edge cases and think adversarially
- Skill in documenting findings clearly and precisely
- Curiosity about how LLMs are built, deployed, and exploited
- Self-motivated and comfortable working without supervision
Nice to have
- Experience with penetration testing or red teaming
- Familiarity with prompt engineering, fine-tuning, or RLHF
- Background in applied cryptography or secure systems design
- Experience with AI safety or alignment research
- Prior work in bug bounty programs or adversarial ML
Stack
- Artificial Intelligence
- Large Language Models
- Cyber Security
- Prompt Engineering
- Vulnerability Analysis
- Machine Learning
- Software Safety
- Trusted Systems
How you'll work
- Fully remote location
- Hourly contract engagement
- 10 to 40 hours per week
- Flexible and asynchronous schedule
- Independent task-based work
What you get
- Work on frontier AI systems with leading labs
- Complete flexibility on when and where to work
- Freelance autonomy with high-impact projects
- Contribute to critical AI safety initiatives
- Potential for ongoing work and contract extension