Agent Security Engineer

Belmont Lavan Ltd; Brazil (IN); On-site; USD 150,000 - 210,000; Full time

Job summary

Belmont Lavan Ltd. is hiring an Agent Security Engineer to secure autonomous AI agents before and after they reach production. You will sit between AI engineering and security, designing guardrails and governance controls that let the business deploy agents with confidence.

You will attack the systems yourself to verify defenses, build monitoring, and ensure identity and access controls are in place. The role requires strong Python skills and hands-on experience with cloud security across AWS,

Qualifications

• 5+ years in security engineering with at least 1 year securing AI agents
• Hands-on knowledge of LLM attack techniques: prompt injection, jailbreaks, data exfiltration via tools
• Experience designing identity and access controls: OAuth 2.0 / OIDC, token exchange, workload identity
• 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

Responsibilities

• Sit between AI engineering and security to align guardrails with business goals
• Design guardrails and governance controls for autonomous AI agents
• Attack the systems to verify defenses and improve resilience
• Collaborate with risk teams and executives to communicate AI risk and mitigations

Skills

Security engineering

LLM/agent security

OAuth 2.0 / OIDC

Identity and access management

Prompt injection

Python

Go/TypeScript/Rust

Cloud security (AWS/Azure/GCP)

Policy as code (OPA/Cedar)

Tools

LangGraph

OpenAI Agents SDK

CrewAI

Model Context Protocol (MCP)

Job description

Belmont Lavan is hiring an Agent Security Engineer to secure autonomous AI agents before and after they reach production. Agents now call tools, hold credentials and act on live systems, so they need the controls we already expect for people and services: identity, least-privilege access, monitoring and testing.

You will sit between AI engineering and security. You will design the guardrails, attack the systems yourself, and build the governance controls that let the business deploy agents with confidence.

• 5+ years in security engineering (AppSec, cloud security, IAM or offensive security), 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