Phaidra · 14 hours ago
Senior Product Security Engineer
United States
Full-time
Remote
Senior Level
£95K/yr - £142K/yr
5+ years expPhaidra is building the future of industrial automation by creating AI-powered control systems for the industrial sector. They are seeking a Senior Product Security Engineer to ensure the security of autonomous agents that optimize operational efficiency in AI factories, tackling unique security challenges associated with these systems.
Artificial Intelligence (AI)Industrial AutomationInformation TechnologyMachine Learning
No H1B
Responsibilities
Champion Secure Agentic AI Development: Drive the adoption of Phaidra’s Secure AI/ML Development Lifecycle (SAIDL) within the Agentic AI team. Adapt 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. Beyond standard AI risks, you will analyze risks unique to agents, such as goal misalignment, reward hacking, infinite looping, and insecure tool execution (e.g., an agent executing a command that exceeds safety limits)
Secure Agent Architecture & Safety Boundaries: Design secure-by-default architectures for autonomous agents. Crucially, this involves defining deterministic safety guardrails that sit between the probabilistic AI model and the physical hardware controls. Ensure "Zero Trust" applies to the agent—it should only have the minimum permissions needed to adjust specific parameters
Secure Agent Tools & Memory: Architect security controls for the "tools" the agent uses (APIs to read sensors or change settings) and the agent's long-term memory. Ensure the agent cannot be manipulated into using a tool to perform unauthorized actions or "poisoned" via its memory context
MLSecOps for RL Pipelines: Secure the training and simulation pipelines used for Reinforcement Learning. Ensure the integrity of the simulation environments (Digital Twins) used to train agents, preventing attackers from influencing agent behavior during the training phase
Adversarial Testing & Red Teaming: Lead AI Red Teaming exercises focused on behavioral manipulation. Can you trick the agent into making a suboptimal decision? Can you manipulate the observations the agent receives?
Incident Preparedness: Develop incident response playbooks tailored for autonomous systems, focusing on "Kill Switches" and rapid rollback capabilities in the event of rogue agent behavior
Cross-Functional Partnership: Build strong relationships with the Agentic AI researchers, SREs, and Data Scientists. Act as an enabler who helps them deploy powerful agents safely, rather than a blocker
Qualification
Required
Proven understanding of the security risks associated with Reinforcement Learning, Autonomous Agents, or automated decision-making systems
Demonstrated experience working embedded with AI system developers and researchers. You understand the difference between 'probabilistic' (AI) and 'deterministic' (Code) and how to secure the bridge between them
5+ years of work experience in product security, application security, or a closely related security engineering role
You understand that in physical systems, 'Availability' and 'Safety' often outrank 'Confidentiality.' You are familiar with concepts like fail-safes and human-in-the-loop controls
Strong programming experience, ideally 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)
Direct, hands-on experience securing MLOps tooling (e.g., Kubeflow, MLflow) and deep understanding of securing complex data and model-training pipelines
Preferred
Experience working with systems that interface with the physical world (IoT, Robotics, ICS/OT). Understanding of the 'IT/OT convergence.'
Experience using mathematical methods to prove that an AI model or agent will not violate specific safety constraints
Experience securing simulation environments (Digital Twins) and managing the security risks of transferring policies from simulation to the real world
Ability to test industrial protocols (e.g., Modbus, BACnet) for robustness against automated or adversarial inputs
Familiarity with emerging standards like the NIST AI RMF or ISO 42001
Experience securing 'closed loops' or control systems where latency and reliability are critical
Relevant advanced certifications, such as GICSP (Global Industrial Cyber Security Professional), ISA/IEC 62443 Cybersecurity Expert, NVIDIA Agentic AI, OSEP (Offensive Security Experienced Penetration Tester), CISSP, or OSCP
Benefits
Fast-paced, team-oriented environment where your work directly shapes the company’s direction.
We are a 100% remote company.
Competitive compensation & meaningful equity.
Outsized responsibilities & professional development.
Training is foundational; functional, customer immersion, and development training.
Medical, dental, and vision insurance (exact benefits vary by region).
Unlimited paid time off, with a required minimum of 20 days per year.
Paid parental leave (exact benefits vary by region).
Flexible stipends to support your workspace, well-being, and continued professional development.
Company MacBook.
Company
Phaidra
Phaidra provides AI and ML solutions to accelerate performance in large-scale industries.
51-200 employees
Funding
Current Stage
Growth StageTotal Funding
$92.5MKey Investors
Collaborative FundAmazonIndex Ventures
2025-10-01Series B· $50M
2024-09-24Grant
2024-07-02Series Unknown· $12M
Leadership Team
Jim Gao
CEO & Co-founder
Katie Hoffman
Co-founder, President & COO
Recent News
Sourcery
2025-10-09
Company data provided by crunchbase