Alignerr is seeking an experienced offensive security professional to train and evaluate frontier AI models. This fully remote, flexible hourly contract role emphasizes structured threat reasoning over exploit development.
You will work on your own schedule, applying adversarial mindset to real-world AI security challenges. Ideal candidates have 2+ years in pentesting/red teaming or blue-team roles, with strong threat modeling and MITRE ATT&CK knowledge.
#J-18808-Ljbffr
AI Security Adversary Analyst — Remote Contract in Manchester employer: Alignerr Corp.
Join a leading global AI research firm that values innovation and collaboration, offering a dynamic remote work environment for an Applied Physicist. With competitive pay, flexible scheduling, and a strong emphasis on employee growth, this role provides the opportunity to engage in cutting-edge projects while contributing to the advancement of AI technology. Experience a supportive culture that encourages creativity and professional development, making it an ideal place for those passionate about physics and AI.
