JobCubby JobCubby
Sign up
Belmont Lavan Ltd

Agent Security Engineer

Belmont Lavan Ltd Berlin, Germany

IT System Custom Software Development · 2-10 employees

20 h ago
Remote security Senior (5-10 yrs) Full-time Germany
Create a free account to apply — email only, no card. You can also save this posting or score it against your profile with AI.

Applying here? Try the free cover letter tool — paste this posting and your résumé, no account needed.

About the role

Design security guardrails and governance controls for autonomous AI agents before and after production deployment. Conduct security testing and attacks against agent systems, and enable confident deployment through identity, access, monitoring, and testing controls.

What they look for

Security Engineering LLM Security AI Agent Security Prompt Injection Jailbreak Testing Data Exfiltration Prevention RAG Security OAuth 2.0 OIDC Identity and Access Management Secrets Management Python Go TypeScript Rust Cloud Security

Requirements

Requires 5+ years of security engineering experience, including at least 1 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 or protocols, strong Python skills plus Go, TypeScript, or Rust, and cloud security across AWS, Azure, or GCP.

Full 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

Similar roles