AI Agent Security Research Engineer

Skills

About the Role

You will design and implement multi-agent code-auditing systems for vulnerability detection, malicious-code identification, and sensitive-information leakage. You will integrate RAG and agent techniques into security audits, develop DevSecOps pipeline plugins, protect LLM applications, automate threat-response workflows, and build scalable agent services and detection APIs.

Requirements

• 3+ years of backend development experience.
• Proficiency in at least one of Python, Go, or Java.
• Hands-on experience deploying LLM agents in production.
• Experience with AI security, including prompt injection, jailbreaking, malicious agent injection, and tool misuse defenses.
• Familiarity with at least one agent framework: LangChain, LlamaIndex, AutoGen, CrewAI, or LangGraph.
• Production project experience with an agent framework.
• Proficiency in Docker and Kubernetes.
• Expertise in microservices architecture design and deployment.

Responsibilities

• Design and implement a multi-agent collaborative code-auditing system for vulnerability detection, malicious-code identification, and sensitive-information leakage.
• Lead planner, executor, and critic role decomposition, tool-invocation chains, and cross-agent state synchronization design.
• Integrate RAG, Chain-of-Thought, and Reflection techniques into security audit agents.
• Optimize detection accuracy and recall, and establish a quantifiable evaluation and iteration framework.
• Develop GitLab CI/CD, Tekton, and Jenkins plugins to enable audit-on-commit workflows.
• Build security protections for LLM applications across input, output, and runtime layers.
• Develop agent workflows for alert classification, contextual correlation, false-positive filtering, and threat-intelligence retrieval.
• Design human-machine intervention mechanisms and agent behavior audit systems.
• Construct highly available, scalable agent services for concurrent scanning-task scheduling and fault tolerance.
• Standardize detection APIs and build rule management, result visualization, and false-positive feedback systems.

Benefits

• Competitive total compensation package.
• Learning and development programs.
• Education subsidy.
• Team-building programs and company events.
• Wellness and meal allowances.
• Comprehensive healthcare schemes for employees and dependants.