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 and experimental nature of Reinforcement Learning and agent development.
• Agentic Threat Modeling: Partner with researchers to model threats specific to autonomous agents, analyzing risks unique to agents such as 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 that sit between the probabilistic AI model and physical hardware controls, applying "Zero Trust" principles.
• MLSecOps for RL Pipelines: Secure the training and simulation pipelines used for Reinforcement Learning, ensuring the integrity of simulation environments (Digital Twins) used to train agents.

This role creates positive change by ensuring the security and safety of AI-powered control systems that optimize industrial facilities, enabling them to automatically learn and improve over time while preventing security failures that could lead to operational downtime or physical degradation of critical hardware.

• Agentic AI & RL Security: Proven understanding of security risks associated with Reinforcement Learning, Autonomous Agents, or automated decision-making systems.
• Core Experience: 5+ years of work experience in product security, application security, or closely related security engineering roles.
• Technical Depth: Strong programming experience with Python (essential for ML/AI ecosystems) or Go, familiarity with agent frameworks (e.g., LangChain, AutoGPT) or RL libraries (e.g., Ray RLLib), proven experience securing Cloud infrastructure (GCP) and Kubernetes, deep understanding of Authentication & Authorization (specifically non-human identities/workload identity).
• Advanced MLOps: Direct, hands-on experience securing MLOps tooling (e.g., Kubeflow, MLflow) and deep understanding of securing complex data and model-training pipelines.

• Competitive compensation & meaningful equity
• Medical, dental, and vision insurance (varies by region)
• Unlimited paid time off, with required minimum of 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
• Training opportunities including functional, customer immersion, and development training

Phaidra creates AI-powered control systems for the industrial sector, enabling industrial facilities to automatically learn and improve over time using reinforcement learning algorithms to convert raw sensor data into high-value actions and decisions.