Agent Security Expert

🗓️ Posted 2026-08-14 Singapore Permanent ICT

Company shared salary

NA

Market rate

NA

Based on similar roles (title + domain + location).

About the Company

We are building the next-generation Agent security product to protect enterprise AI workloads at scale. As our Agent Security Expert, you will define the technical architecture for real-time agent defense and lead the product's security roadmap in a fast-emerging global market. You will work at the intersection of application security, AI safety, and systems engineering, shaping how enterprises safely deploy autonomous agents across their digital infrastructure.

Responsibilities

  • Own the end-to-end technical architecture of our Agent security product, making principled trade-offs across detection coverage, latency, and operational overhead.
  • Design and implement runtime guardrails - including prompt injection defense, unauthorized tool-call interception, behavioral drift detection, and real-time credential leak prevention.
  • Architect MCP and tool-chain supply-chain security capabilities against tool poisoning, cross-origin privilege escalation, and transitive trust abuse.
  • Build an automated agent red-teaming pipeline to continuously discover vulnerabilities, generate adversarial test cases, and harden defenses before production deployment.
  • Partner with product, engineering, and threat intelligence teams to translate emerging attack patterns into shipped security features, and mentor junior engineers on security-first design.

Requirements

  • 8+ years of hands-on experience in security engineering, systems engineering, or a closely related field, with a track record of shipping production security components.
  • Deep expertise in at least two of: application security, cloud-native security, identity and access management (IAM), or offensive/defensive security operations.
  • Proficient in at least two of Go, Python, Rust, or C++, with experience building high-concurrency security services or detection pipelines.
  • Strong working knowledge of the LLM/Agent stack - RAG architectures, function calling, MCP protocol, and mainstream agent frameworks - and the unique attack surfaces they introduce.
  • Experience researching or shipping enterprise security products (EDR, CNAPP, AI-SPM, or equivalent); familiarity with sandboxing, eBPF, or container/virtualization isolation is a strong plus.