AI Security Engineer
Role Overview
This senior-level AI Security Engineer role involves designing and implementing security mechanisms for AI systems, including self-hosted models and LLM APIs, to protect against adversarial threats. Day-to-day responsibilities include hands-on remediation, threat modeling, and conducting security assessments in a cross-functional team environment, ensuring the AI stack is secure by default.
Perks & Benefits
The role is fully remote, offering flexibility in location and likely a supportive tech culture focused on innovation and security. It provides opportunities for career growth through technical leadership and project ownership, with an emphasis on collaboration and continuous learning in AI security.
Full Job Description
Perplexity is seeking a highly skilled, experienced, and hands-on AI Security Engineer to join our security team, driving the protection of next-generation AI systems against adversarial threats. In this role, you’ll design and implement robust mechanisms to secure self-hosted models, LLM APIs, agents, MCPs, and the core AI stack. You'll empower developers with tools and guidance, as well as technical contributions, enabling innovation while ensuring AI security is strong by default.
Our tech stack includes Python, NextJS, TypeScript, Docker, AWS, Kubernetes, and PostgreSQL.
Responsibilities
Define, build, and refine mechanisms to secure AI systems (including self-hosted models, LLM APIs, agents, MCPs, and other core components of the AI stack) against adversarial behavior of all kinds
Understand technically complex AI systems, identify potential weaknesses in their architecture, and implement improvements
At least 50% of time performing hands-on remediation. Also working closely with peer engineers to drive remediations
Plan and carry out threat modeling activities and realistic threat simulations across our offerings
Conduct cybersecurity evaluations and lead AI security assessments in a cross-functional environment
Develop initiatives that improve our capabilities to effectively evaluate AI systems and enhance the organization's prevention, detection, response, and threat hunting capabilities
Provide guidance and education to developers to help deter and prevent threats
Qualifications
Hands-on coding and prompting experience.
Bachelor of Science or Master of Science in Computer Science or a related field, or equivalent experience
Be a technical and process subject matter expert regarding AI security services and attacker tactics, techniques, and procedures
Good understanding of LLMs, AI architecture patterns, machine learning models, and related technologies such as MCP
Understanding of application security principles and secure coding practices
Experience developing and implementing security procedures and policies
Strong problem-solving, project management, leadership, and communication skills
Self-motivated with a willingness to take ownership of tasks
4+ years of industry experience
Similar jobs
Found 6 similar jobs