Senior Engineer Vulnerability Scanner

Who We Are
OKX will be prioritising applicants who have a current right to work in Singapore, and do not require OKXs sponsorship of a visa.

At OKX, we believe that the future will be reshaped by crypto, and ultimately contribute to every individuals freedom. OKX is a leading crypto exchange, and the developer of OKX Wallet, giving millions access to crypto trading and decentralized crypto applications (dApps). OKX is also a trusted brand by hundreds of large institutions seeking access to crypto markets. We are safe and reliable, backed by our Proof of Reserves. Across our multiple offices globally, we are united by our core principles: We Before Me, Do the Right Thing, and Get Things Done. These shared values drive our culture, shape our processes, and foster a friendly, rewarding, and diverse environment for every OK-er. OKX is part of OKG, a group that brings the value of Blockchain to users around the world, through our leading products OKX, OKX Wallet, OKLink and more.

About the Opportunity
Our Security Engineering team is building AI-driven security infrastructure to protect OKXs LLM applications and developer pipelines at scale. This role sits at the intersection of agentic AI and security engineering — designing multi‑agent systems, building detection engines, and embedding security into our development lifecycle. If youre passionate about solving real‑world AI security challenges in a fast‑moving environment, wed love to hear from you.

What You’ll Be Doing

Design and ship a Multi-Agent code auditing system (vulnerability detection, malicious code, sensitive data leakage) including role decomposition, tool‑calling pipelines, and cross‑agent state synchronization

Integrate RAG, Chain‑of‑Thought, and Reflection techniques into security audit agents; build evaluation frameworks to continuously improve detection accuracy

Develop CI/CD plugins for GitLab, Tekton, and Jenkins to enable automated security audit on every commit

Build an LLM security framework covering input, output and runtime

Design Human‑in‑the‑loop and agent behavior audit systems ensuring production agents are observable, traceable, and controllable

What We Look For In You

3+ years of backend development in Python, Go, or Java

End-to-end LLM Agent production experience with depth in architecture design, hallucination handling, and tool‑call fault tolerance

Hands‑on AI security knowledge — Prompt Injection, Jailbreak, malicious agent injection, tool misuse — with production‑ready defensive solutions

Production experience with at least one of LangChain, LlamaIndex, AutoGen, CrewAI, or LangGraph

Proficiency with Docker, Kubernetes, and microservice architecture

Nice to Haves

SAST/SCA or code auditing tool experience

LLM fine‑tuning or local model deployment; security‑domain fine‑tuning is a strong plus

Open source agent projects on GitHub or merged PRs to mainstream LLM frameworks

CTF awards or CVE/CNVD submission records

Perks & Benefits

Competitive total compensation package

L&D programs and Education subsidy for employees growth and development

Various team building programs and company events

Wellness and meal allowances

Comprehensive healthcare schemes for employees and dependants

#J-18808-Ljbffr