AI Agent Security Research Engineer

职位要求 / 描述

<div data-page-id="Y7HSd59lcoI1BGxLy8jlqxZKgTg" data-lark-html-role="root" data-docx-has-block-data="false"> <div class="ace-line ace-line old-record-id-Gvrsd3KZkoiEpQxM1qRlAn4Ngta"> <div data-page-id="Y7HSd59lcoI1BGxLy8jlqxZKgTg" data-lark-html-role="root" data-docx-has-block-data="false"> <div class="ace-line ace-line old-record-id-YWZkd982CopaXcxaoNglKtLOgqb"><br> <h2><strong>Who We Are</strong></h2> <p>At OKX, we believe that the future will be reshaped by crypto, and ultimately contribute to every individual's freedom. </p> <p>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.</p> <p>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.</p> <p>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.</p> <div data-page-id="DEWydktFLo4ARlxtqUuu9DX4sAd" data-lark-html-role="root" data-docx-has-block-data="false"> <div class="ace-line ace-line old-record-id-Vclfd4PL7opuBCxw8PXupTossVg"> <p><strong><br>Responsibilities</strong></p> <ul> <li class="ace-line ace-line old-record-id-A8TCd02Myo7fhcxwrsglP0lKgfc" data-list="number"> <div>AI-Driven Code Security Detection Engine</div> <ol class="list-number2"> <li class="ace-line ace-line old-record-id-RP4DdZH9cocSPyxbZiylWX9tg9K" data-list="bullet"> <div> <p>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.</p> </div> </li> <li class="ace-line ace-line old-record-id-ZrhZdOhCjoZQsZx88GDlZtqEgVh" data-list="bullet"> <div>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.</div> </li> <li class="ace-line ace-line old-record-id-LsIOdkmU2oCfidxsUpxlTyN1geb" data-list="bullet"> <div>Deeply integrate with DevSecOps workflows. Develop plugins for mainstream pipelines like GitLab CI/CD, Tekton, and Jenkins to achieve “audit-on-commit.”</div> </li> </ol> </li> <li class="ace-line ace-line old-record-id-PGeGdCqPnoePPjxzr00lWmnxg4y" data-list="number"> <div>AI System Security Protection and Threat Response</div> <ol class="list-number2"> <li class="ace-line ace-line old-record-id-D6tydMJOeo6UpfxElftlqdTIgWb" data-list="bullet"> <div> <p>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).</p> </div> </li> <li class="ace-line ace-line old-record-id-YstAdO1P8opg0yxGH0clpEkwgUd" data-list="bullet"> <div>Develop Agent workflows for automated alert classification, contextual correlation, and false positive filtering. Integrate RAG-driven threat intelligence retrieval to generate automated analysis conclusions, supporting SOAR platform integration.</div> </li> <li class="ace-line ace-line old-record-id-RjfEd62uboA18pxwlOflK9XSgsg" data-list="bullet"> <div>Design human-machine collaboration intervention mechanisms and Agent behavior audit systems to ensure observability, traceability, and intervenability of Agent actions in production environment

技能关键字

职责方向