Agent Security Expert

Position Overview

We are developing an advanced Agent security solution aimed at safeguarding enterprise AI workloads on a large scale. In the role of Agent Security Expert, you will be responsible for establishing the technical framework for real-time agent protection and directing the security development roadmap for this cutting-edge product in a fast-growing global landscape. This position requires working at the crossroads of application security, AI safety, and systems engineering to innovate secure deployment methods for autonomous agents within enterprise digital environments.

Key Responsibilities

• Lead the complete technical architecture design for the Agent security product, balancing detection effectiveness, response latency, and operational efficiency.
• Create and deploy runtime security measures such as defenses against prompt injection, interception of unauthorized tool commands, behavioral anomaly detection, and immediate credential leak prevention.
• Design secure supply-chain mechanisms for MCP and tool-chains to guard against risks like tool tampering, cross-origin privilege escalation, and abusive transitive trust.
• Develop and maintain an automated agent red-teaming system to continuously identify vulnerabilities, produce adversarial test scenarios, and reinforce defenses prior to deployment.
• Collaborate closely with product managers, engineering teams, and threat intelligence groups to convert recognized attack techniques into implemented security features and provide mentorship to junior engineers focusing on security-first design principles.

Qualifications

• At least eight years of hands-on experience in security engineering, systems engineering, or a closely related discipline, with demonstrable success delivering production-ready security components.
• Strong expertise in a minimum of two areas such as application security, cloud-native security, identity and access management (IAM), or offensive/defensive security operations.
• Proficiency in at least two programming languages among Go, Python, Rust, or C++, with experience crafting high-concurrency security services or threat detection pipelines.
• In-depth understanding of the large language model (LLM) and agent ecosystems, including RAG architectures, function calling mechanisms, MCP protocols, and common agent frameworks, with awareness of the specific vulnerabilities these present.
• Experience developing or researching enterprise security solutions like endpoint detection and response (EDR), cloud native application protection platform (CNAPP), AI security posture management (AI-SPM), or related products; knowledge of sandboxing technologies, extended Berkeley Packet Filter (eBPF), or container/virtualization isolation is advantageous.