Senior Product Security Engineer

• Champion Secure Agentic AI Development: Drive the adoption of Phaidra's Secure AI/ML Development Lifecycle (SAIDL) within the Agentic AI team, adapting security practices to fit the iterative nature of Reinforcement Learning and agent development.
• Agentic Threat Modeling: Partner with researchers to model threats specific to autonomous agents, analyzing risks like goal misalignment, reward hacking, infinite looping, and insecure tool execution.
• Secure Agent Architecture & Safety Boundaries: Design secure-by-default architectures for autonomous agents, defining deterministic safety guardrails between AI models and physical hardware controls.
• MLSecOps for RL Pipelines: Secure training and simulation pipelines for Reinforcement Learning, ensuring integrity of simulation environments and preventing manipulation during training.

This role creates positive change by ensuring the security and integrity of AI-driven autonomous agents that optimize industrial facilities, preventing operational downtime and physical degradation of critical hardware while enabling more efficient and stable environments for massive-scale compute.

• Agentic AI & RL Security: Proven understanding of security risks associated with Reinforcement Learning, Autonomous Agents, or automated decision-making systems.
• Core Experience: 5+ years in product security, application security, or closely related security engineering roles.
• Technical Depth: Strong programming experience with Python or Go, familiarity with agent frameworks or RL libraries, experience securing Cloud infrastructure (GCP) and Kubernetes, deep understanding of Authentication & Authorization.
• Advanced MLOps: Direct hands-on experience securing MLOps tooling and complex data/model-training pipelines.

• Competitive compensation & meaningful equity
• Medical, dental, and vision insurance (varies by region)
• Unlimited paid time off with minimum 20 days per year
• Paid parental leave (varies by region)
• Flexible stipends for workspace, well-being, and professional development
• Company MacBook
• 100% remote work environment
• Fast-paced, team-oriented environment with outsized responsibilities
• Professional development and training opportunities

Phaidra creates AI-powered control systems for the industrial sector, using reinforcement learning algorithms to enable industrial facilities to automatically learn and improve over time, with a focus on optimizing power usage, cooling efficiency, and hardware health in critical infrastructure.