At a Glance
- Tasks: Probe frontier AI models and identify vulnerabilities to enhance AI security.
- Company: Alignerr, a leader in AI safety and reliability.
- Benefits: Flexible remote work, autonomy in scheduling, and competitive hourly pay.
- Other info: Join a dynamic team dedicated to advancing AI safety.
- Why this job: Shape the future of AI by ensuring its safe and reliable use.
- Qualifications: Experience in AI security analysis and understanding of threat modeling.
The predicted salary is between 31.5 - 38.5 £ per hour.
Alignerr is seeking an AI Security Analyst to probe frontier AI models, identify vulnerabilities, and help shape safe, reliable AI systems that resist misuse.
You will analyze real-world AI and LLM security scenarios to understand model behavior under adversarial conditions.
This fully remote, hourly contract offers flexible, asynchronous work and the autonomy to manage your own schedule.
You will review prompt injection, data leakage, and system abuse cases, apply threat modeling frameworks,
#J-18808-Ljbffr
Remote AI Security Analyst - Frontier Model Vetting employer: Alignerr
Alignerr is an exceptional employer that champions innovation in healthcare through AI, offering a dynamic remote work environment that fosters collaboration and creativity. Employees benefit from a culture of continuous learning and professional development, with ample opportunities to grow within the organisation while contributing to groundbreaking projects that have a real impact on clinical research. Join us to be part of a forward-thinking team dedicated to transforming healthcare for the better.
