Senior Engineer, AI Agent Security Research

Confirmed live in the last 24 hours

OKX

Office Locations

On-site

Posted March 3, 2026

Job Description

OKX will be prioritising applicants who have a current right to work in Singapore, and do not require OKX's sponsorship of a visa.

Who We Are

At OKX, we believe that the future will be reshaped by Crypto, ultimately contributing to every individual's freedom.

OKX began as a crypto exchange giving millions of people access to crypto trading and over time becoming among the largest platforms in the world. In recent years, we have developed one of the most connected Web3 wallets used by millions to access decentralized crypto applications (dApps).

OKX is a trusted brand by hundreds of large institutions seeking access to crypto markets on a reliable platform that seamlessly connects with global banking and payments. In the last year, OKX has expanded into new markets including Australia, Brazil, Netherlands, Singapore and Turkey, with plans to launch in the US, Belgium and the UAE.

We are deeply committed to shaping a fairer, more transparent and accessible society through blockchain technology. This is why we publish proof of reserves monthly, and continue to ship new innovative security features.

What You’ll Be Doing

AI-Driven Code Security Detection Engine
1. 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.
2. Integrate RAG, Chain-of-Thought, Reflection, and other technologies into security audit agents. Continuously optimize detection accuracy and recall rates while establishing a quantifiable evaluation and iteration framework.
3. Deeply integrate with DevSecOps workflows. Develop plugins for mainstream pipelines like GitLab CI/CD, Tekton, and Jenkins to achieve “audit-on-commit.”
AI System Security Protection and Threat Response
1. Responsible for constructing a security protection framework for large language model applications, covering three dimensions: input layer (prompt injection, jailbreak detection), output layer (sensitive information leakage, compliance auditing), and runtime (tool invocation sandboxing, anomaly behavior circuit breaking).
2. Develop Agent workflows for automated alert classification, contextual correlation, and false positive fi