Agent Security Engineer
- Vancouver, BC, Canada
Full-time
Applications open in a new tab.
Job details
- Job type
- Full-time
- Apply by
- 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.
Requirements
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.
Requirements
- 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
Design security guardrails and governance controls for autonomous AI agents before and after production deployment. Test agent systems for attacks and help the business deploy agents securely and confidently.
Requirements
Requires at least five years of security engineering experience, including at least one year securing LLM or agent-based systems, and hands-on knowledge of LLM attack techniques. Candidates should have experience with identity and access controls, agent frameworks, Python and another listed programming language, cloud security, monitoring, and policy-as-code, as well as the ability to communicate AI risks to technical and business audiences.
Skills
- Security Engineering
- AI Agent Security
- LLM Security
- Prompt Injection Defense
- Identity and Access Management
- OAuth 2.0
- OpenID Connect
- Python
- Go
- TypeScript
- Rust
- Cloud Security
- Threat Detection
- Policy as Code
- Penetration Testing
- Risk Communication
Visa sponsorship
Not detected in the job text
Categories
- Security & Safety
- Technology
- Software
Keywords
- Autonomous AI Agents
- LLM Security
- Agent Security
- Application Security
- Cloud Security
- Identity and Access Management
- Prompt Injection
- Jailbreaks
- Data Exfiltration
- RAG Poisoning
- OAuth 2.0
- OpenID Connect
- Token Exchange
- Workload Identity
- Secrets Management
- LangGraph
- OpenAI Agents SDK
- CrewAI
- Model Context Protocol
- Python
- Go
- TypeScript
- Rust
- AWS
- Azure
- Google Cloud Platform
- Logging
- Threat Detection
- Policy as Code
- OPA