Agent Security Engineer

Belmont Lavan Ltd • Brazil, IN

4d

About The Position

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

Requirements

• At least 5 years of experience in security engineering, such as application security, cloud security, identity and access management, 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 Python coding skills and proficiency in at least 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

• Design security guardrails for autonomous AI agents.
• Attack and test agent systems hands-on.
• Build governance controls that support secure deployment of agents.
• Secure agents before and after they reach production.

What This Job Offers

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