Agent Security Expert

About the role

Tencent's Cloud & Smart Industries Group (CSIG) is building the next-generation Agent security product to protect enterprise AI workloads at scale. As Agent Security Expert, you will define the technical architecture for real-time agent defense and lead the product's security roadmap, working at the intersection of application security, AI safety and systems engineering.

Key responsibilities

• Own the end-to-end technical architecture of the Agent security product, balancing 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 against tool poisoning, cross-origin privilege escalation and transitive trust abuse.
• Build an automated agent red-teaming pipeline to discover vulnerabilities, generate adversarial test cases and harden defenses before production.
• Partner with product, engineering and threat intelligence teams to turn emerging attack patterns into shipped security features, and mentor junior engineers on security-first design.

Required profile

• 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, IAM, or offensive/defensive security operations.
• Experience researching or shipping enterprise security products (EDR, CNAPP, AI-SPM or equivalent); sandboxing, eBPF or container/virtualization isolation is a strong plus.

Required skills

• Proficiency in at least two of Go, Python, Rust or C++ for high-concurrency security services or detection pipelines.
• Strong knowledge of the LLM/Agent stack: RAG architectures, function calling, MCP protocol and mainstream agent frameworks.