Agent Security Engineer

Belmont Lavan • Texas City, TX

3d

About The Position

Belmont Lavan is hiring an Agent Security Engineer to secure autonomous AI agents before and after they reach production. Because agents can call tools, hold credentials, and act on live systems, the role focuses on applying controls such as identity, least-privilege access, monitoring, and testing. The position sits between AI engineering and security, designing guardrails, testing systems through offensive security work, and building governance controls that enable the business to deploy agents with confidence.

Requirements

• At least 5 years of experience in security engineering, such as AppSec, cloud security, IAM, or offensive security.
• At least 1 year of experience securing LLM or agent-based systems.
• Hands-on knowledge of LLM attack techniques, including prompt injection, jailbreaks, data exfiltration via tools, and RAG poisoning.
• Experience designing identity and access controls, including OAuth 2.0 / OIDC, token exchange, workload identity, and secrets management.
• Working knowledge of agent frameworks and protocols such as LangGraph, OpenAI Agents SDK, CrewAI, or Model Context Protocol (MCP).
• Strong coding skills in Python and one of Go, TypeScript, or Rust.
• Cloud security experience on AWS, Azure, or GCP, including logging, detection, and policy-as-code such as OPA or Cedar.
• Ability to explain AI risk clearly to engineers, risk teams, and executives.

Responsibilities

• Secure autonomous AI agents before and after they reach production.
• Design guardrails and identity and least-privilege access controls for AI agents.
• Test agent systems by attacking them and assessing their security.
• Build governance controls that support confident business deployment of agents.
• Apply monitoring and testing controls to agents operating on live systems.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed