OKX

3 months ago

AI Agent Security Research Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 7 hours agoStatus: Live

Job Summary

Design and build a multi-agent, AI-driven code security auditing system to detect vulnerabilities, malicious code, and information leakage. Lead role decomposition of planners/executors/critics, integrate RAG and other AI techniques, and ensure security audit capabilities within DevSecOps workflows, including audit-on-commit pipelines.

Location: Hong Kong, Singapore

Workplace: Onsite

Job Function: Research & Scientific (R&D)

Key Responsibilities

•AI-Driven Code Security Detection Engine: Design and implement a multi-agent collaborative code auditing system covering vulnerability detection, malicious code identification, and sensitive information leakage scenarios; lead the role decomposition of Planners/Executors/Critics, tool invocation chains, and cross-agent state synchronization mechanism design.
•Integrate RAG, Chain-of-Thought, Reflection, and other technologies into security audit agents; continuously optimize detection accuracy and recall rates with a quantified evaluation framework.
•Deeply integrate with DevSecOps workflows; develop plugins for pipelines like GitLab CI/CD, Tekton, and Jenkins to achieve audit-on-commit.
•AI System Security Protection and Threat Response: Build a security framework for large language model applications across input, output, and runtime layers (prompt injection, leakage, sandboxing, anomaly detection).
•Engineering Development and Platform Services: Construct a highly available, scalable Agent service architecture and standardize API output for detection capabilities with closed-loop tooling for rule management and visualization.

Key Requirements

•Development experience: 3+ years of backend development, proficient in at least one of Python/Go/Java, with a solid engineering foundation.
•Agent implementation & security: Hands-on experience deploying LLM Agents, capable of detailing engineering challenges such as agent architecture design, hallucination handling, and tool invocation fault tolerance; knowledge of AI security risks and defense strategies.
•Framework proficiency: Familiarity with at least one agent framework (LangChain, LlamaIndex, AutoGen, CrewAI, or LangGraph) with production project experience.
•Engineering capabilities: Proficient in Docker and Kubernetes, with expertise in microservices architecture design and deployment.
•Preferred: Security tool experience (SAST/SCA), or code auditing tooling (CodeQL, Semgrep, SonarQube); open to model fine-tuning and security-domain experience.

Experience:3+ years

Skills:Problem-solvingCollaboration

Tech Stack:PythonGoJavaDockerKubernetesLangChainLlamaIndexAutoGenCrewAILangGraphGitLab CI/CDTektonJenkins

Company Brief

OKX

Global cryptocurrency exchange and Web3 technology provider offering spot and derivatives trading, custody, wallet services, and blockchain infrastructure to retail and institutional users worldwide.

Industry: Trading Platforms

Company Size: Enterprise (1,001+ employees)

Growth: Established Company

Headquarters: Victoria, Seychelles

Founded: 2017

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

OKX