Senior Product Security Engineer - Agentic AI
P
PhaidraIndustrial Automation
UK or US (central and eastern time preferred), central and eastern time preferredFull-TimeSenior
Salary123520 - 199600 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- DockerPythonGCPKubeflowKubernetesMLFlowPyTorchGoTensorflowTerraformMLOpsLangChain
Requirements
- 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.
- 5+ years of work experience in product security, application security, or a closely related security engineering role.
- Safety Engineering Mindset: Understand that in physical systems, "Availability" and "Safety" often outrank "Confidentiality."
- Strong programming experience, ideally with Python 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.
Responsibilities
- Champion Secure Agentic AI Development: Drive the adoption of Phaidra’s Secure AI/ML Development Lifecycle (SAIDL) within the Agentic AI team.
- 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.
- 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.
- MLSecOps for RL Pipelines: Secure the training and simulation pipelines used for Reinforcement Learning.
- Adversarial Testing & Red Teaming: Lead AI Red Teaming exercises focused on behavioral manipulation.
- Incident Preparedness: Develop incident response playbooks tailored for autonomous systems, focusing on "Kill Switches" and rapid rollback capabilities.
- Cross-Functional Partnership: Build strong relationships with the Agentic AI researchers, SREs, and Data Scientists.
View Full Description & ApplyYou'll be redirected to the employer's site
