Agent Security Engineer
- Remote, Canada
Remote
Full-time
Applications open in a new tab.
Job details
- Job type
- Full-time
- Workplace
- Remote
- Posting language
- English
- Posted
Original 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
More about this job
Responsibilities
You will design security guardrails and governance controls to secure autonomous AI agents throughout their lifecycle. Additionally, you will perform offensive security testing on systems to ensure agents can be deployed with confidence.
Requirements
Candidates must have 5+ years of experience in security engineering with at least 1 year specifically focused on LLM or agent-based systems. Proficiency in Python and experience with cloud security, identity management, and AI-specific attack vectors is required.
Skills
- Security Engineering
- AppSec
- Cloud Security
- IAM
- Offensive Security
- LLM Security
- Prompt Injection
- Jailbreaks
- OAuth 2.0
- OIDC
- Secrets Management
- Python
- Go
- TypeScript
- Rust
- Policy-as-code
Visa sponsorship
Not detected in the job text
Categories
- Technology
- Security & Safety
- Software
- Engineering
- Data & Analytics
Keywords
- Agent Security Engineer
- Autonomous AI Agents
- AppSec
- Cloud Security
- IAM
- Offensive Security
- LLM
- Prompt Injection
- Jailbreaks
- Data Exfiltration
- RAG Poisoning
- OAuth 2.0
- OIDC
- Token Exchange
- Workload Identity
- Secrets Management
- LangGraph
- OpenAI Agents SDK
- CrewAI
- Model Context Protocol
- Python
- Go
- TypeScript
- Rust
- AWS
- Azure
- GCP
- Logging
- Detection
- Policy-as-code