We are in search of an AI Security – Senior Staff Engineer to join our dynamic team, focusing on AI safety and cybersecurity. Ideal candidates will be deeply passionate about AI security, possess a strong background in offensive security techniques, and be eager to take on challenges related to AI-driven cybersecurity threats. We value individuals who are adept in both traditional security approaches and the unique challenges posed by AI and ML technologies.


What you’ll be doing

  • Identifying and evaluating offensive security capabilities within AI frontier models, particularly in relation to adversarial cybersecurity operations.
  • Developing and refining AI model evaluations to assess potential security risks, employing advanced ML and AI techniques.
  • Building and maintaining scalable systems and processes to support AI safety evaluations and threat mitigation strategies.
  • Collaborating with multi-functional teams, including researchers, ML engineers, and security experts, to develop and implement best-in-class security solutions for AI systems.
  • Proactively identifying and mitigating Responsible AI vulnerabilities within large-scale AI systems.
  • Researching emerging threats and developing new methodologies to enhance AI safety and security.


What you bring to the role


Basic Qualifications

  • Bachelor’s degree in Computer Science/Engineering, Cyber Operations/Cybersecurity, AI, or a related field, with 5+ years of relevant experience.
  • Strong expertise in offensive security, adversary tactics, vulnerability research, and exploit development.
  • Hands-on experience with AI/ML technologies, including proficiency in Python, Rust, Go, and ML frameworks like TensorFlow, PyTorch, Keras.
  • Demonstrated experience in red-team and penetration testing engagements.
  • Excellent communication skills, with the ability to articulate complex technical findings to diverse teams.


Preferred Qualifications

  • Advanced degree in a relevant field and/or relevant certifications in cybersecurity or AI.
  • Experience with ML research engineering, ML observability, and large language model-enabled applications.
  • Familiarity with societal aspects of AI deployment and responsible AI principles
  • Familiarity with agent-based systems, automated planning, and AI development simulation models.
  • Proven track record in applying AI/ML methods to cyber domain problems.
Job Overview
Job alerts

Subscribe to our weekly job alerts below and never miss the latest jobs

Sign in

Sign Up

Forgotten Password

Job Quick Search