AI Agent Security Engineer: Guardrails & IAM

Belmont Lavan Ltd; Texas City (TX); Presencial; USD 140.000 - 190.000; Jornada completa

Descripción de la vacante

Belmont Lavan Ltd. is seeking an Agent Security Engineer to secure autonomous AI agents before and after production. You’ll design guardrails, test systems, and build governance that enables confident deployments of agents with minimal risk.

You will join between AI engineering and security, translating risk into concrete controls and policies, and spearheading IAM, least-privilege, monitoring, and testing for live agent-based workflows.

Formación

• 5+ years in security engineering with at least 1 year securing LLM or agent-based systems.
• Hands-on knowledge of LLM attack techniques: prompt injection, jailbreaks, data exfiltration via tools, RAG poisoning
• Experience designing identity and access controls: OAuth 2.0 / OIDC, token exchange, workload identity, 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, plus one of Go, TypeScript or Rust
• Cloud security on AWS, Azure or GCP, including logging, detection and policy-as-code (e.g. OPA / Cedar)
• Ability to explain AI risk clearly to engineers, risk teams and executives

Responsabilidades

• Sit between AI engineering and security to design guardrails and governance controls.
• Attack the systems to validate defenses and ensure secure deployment of agents.
• Collaborate with risk teams and executives to communicate AI risk clearly.

Conocimientos

Security engineering

LLM/agent security

Attack techniques

Identity & access controls

Python

Go/TypeScript/Rust

Cloud security

Explaining AI risk

Herramientas

LangGraph

OpenAI Agents SDK

CrewAI

Model Context Protocol (MCP)

AWS

Azure

GCP

Descripción del empleo

Belmont Lavan Ltd. is seeking an Agent Security Engineer to secure autonomous AI agents before and after production. You’ll design guardrails, test systems, and build governance that enables confident deployments of agents with minimal risk.

You will join between AI engineering and security, translating risk into concrete controls and policies, and spearheading IAM, least-privilege, monitoring, and testing for live agent-based workflows.