Pay Β· estimate~$105k β $145kMarket rate Β· not set by employer
PostedNov 20, 2026
LevelMid level
In short
As we deploy AI agents across trading, risk, compliance, and customer systems, we're building the security architecture that keeps those systems trustworthy at scale.
AWSLLM
π About the job
π’About the Role
As we deploy AI agents across trading, risk, compliance, and customer systems, we're building the security architecture that keeps those systems trustworthy at scale.
This isn't a compliance checkbox role. You'll architect the security layer for systems where a compromised AI agent can authorize transactions, move funds, or access millions of user records. The threat model includes nation-state actors, sophisticated financial fraud, and the exact class of autonomous AI attack campaigns that are actively targeting financial infrastructure today.
You'll work directly with Group Risk & Security leadership to define how we build, deploy, and operate AI safely β from model selection to runtime monitoring to red team automation.
β Key Responsibilities
β AI System Security Architecture
β Design end-to-end security architecture for AI stack: LLM inference pipelines, AI agents, MCP-based tool orchestration, and agentic workflows
β Define trust boundaries, authorization models, and least-privilege principles for multi-agent systems
β Architect the AI Security Gateway: prompt/response inspection, rate limiting, anomaly detection, circuit breaking across all AI-powered products
β Threat Modeling & Red Teaming
β Build and operate an AI-specific threat model covering prompt injection, jailbreak, model inversion, supply chain poisoning, and autonomous agent misuse
β Lead red team exercises against our AI deployments; evolve our Red vs Blue automation platform (currently in production, LLM-driven)
β Define detection signatures for AI-assisted attacks β we've seen the Hermes/Strix/Cairn class of autonomous attack campaigns firsthand
β Secure AI Development Lifecycle (AI-SDL)
β Define security review processes for AI features: model selection, fine-tuning pipelines, RAG system design, tool call authorization
β Evaluate third-party AI vendors and integrations (model APIs, vector DBs, agent frameworks) for security posture
β Work with product and infra teams to embed security requirements from design through deployment
β TEE & Confidential Computing
β Architect TEE-based deployments for sensitive AI inference (AMD SEV-SNP, Nvidia Confidential Computing)
β Design attestation flows, measurement coverage, and post-deployment verification β with the rigor of a Trail of Bits-level audit
β Required
β 6+ years in security engineering or architecture; 2+ years focused on ML/AI systems
β Deep understanding of LLM internals: pretraining, RLHF, inference, safetyβ¦