AI Agent Security Research Engineer at OKX - ScoutJobs - The AI-curated global job board
Skip to content
OKX
Posted 3 days ago

AI Agent Security Research Engineer

OKXAI Agent Security Research Engineer

Perks & benefits

Education AllowanceHealth InsuranceMedical InsuranceRelocation AllowanceVisa

Requirements

3+ years backend development, Proficiency in Python, Go, or Java, Experience deploying LLM Agents, Knowledge of prompt injection and jailbreaking, Familiarity with LangChain, LlamaIndex, or AutoGen, Proficiency in Docker and Kubernetes

Skills

PythonGoLLMDockerKubernetesLangChain

About the role

Responsibilities

  • Design and implement a multi-agent collaborative code auditing system for vulnerability detection and malicious code identification.
  • Integrate RAG, Chain-of-Thought, and Reflection technologies into security audit agents to optimize detection accuracy.
  • Develop security protection frameworks for LLM applications, covering prompt injection, jailbreak detection, and sensitive information leakage.
  • Construct highly available and scalable Agent service architectures to support large-scale concurrent scanning tasks.
  • Integrate security tools into DevSecOps workflows, including plugins for GitLab CI/CD, Tekton, and Jenkins.
  • Design human-machine collaboration mechanisms and Agent behavior audit systems to ensure observability and traceability.

Requirements

  • 3+ years of backend development experience with proficiency in Python, Go, or Java.
  • Hands-on experience deploying LLM Agents in production environments, including handling architecture design and tool invocation.
  • Deep understanding of AI security risks such as prompt injection, jailbreaking, and malicious agent injection.
  • Proficiency with agent frameworks like LangChain, LlamaIndex, AutoGen, CrewAI, or LangGraph.
  • Strong engineering skills with proficiency in Docker and Kubernetes and microservices architecture.

Preferred Qualifications

  • Experience with SAST/SCA tools or code auditing tools like CodeQL, Semgrep, or SonarQube.
  • Experience with LLM fine-tuning (SFT, LoRA) or local deployment of models like Llama 3, Qwen, or DeepSeek.
  • High-quality open-source contributions related to AI agents or mainstream LLM frameworks.
  • A track record of success in CTF competitions or submitting CVE/CNVD vulnerabilities.

Benefits

  • Competitive total compensation package.
  • Learning and development programs and education subsidies.
  • Various team building programs and company events.
  • Wellness and meal allowances.
  • Comprehensive healthcare schemes for employees and dependents.

About the Company

OKX is a leading crypto exchange and the developer of OKX Wallet, providing millions of users access to crypto trading and decentralized applications. We are a trusted brand for large institutions, backed by our Proof of Reserves, and driven by our core principles: We Before Me, Do the Right Thing, and Get Things Done.

ScoutJobs Agent

Get matches like this delivered daily

Sign up free — we'll pull jobs that fit your CV from across the web and rank them for you.

Get started — it's free

AI Agent Security Research Engineer

OKX · Hong Kong

Sign up to apply