AI Cybersecurity Researcher

You will research the intersection of AI and cybersecurity. You will develop AI cybersecurity benchmarks, investigate automated offensive and defensive techniques, model AI-enabled cyber risks, create mitigation frameworks, and integrate security capabilities into evaluation platforms and services.

Responsibilities

• Design and build cybersecurity capability and safety benchmarks for large models and AI agents
• Curate evaluation datasets and write automated benchmark execution code
• Research AI-driven vulnerability discovery, attack-chain generation, malicious-request detection, and vulnerability patching
• Investigate defenses for model services, agent frameworks, and multi-agent systems
• Build quantitative risk models for AI misuse in cyberattacks
• Evaluate the offense-defense balance and propose risk-mitigation frameworks
• Integrate cybersecurity benchmarks, automated offense-defense frameworks, and risk modeling into platforms and evaluation services
• Conduct cybersecurity evaluations and security hardening for client AI systems

Requirements

• Bachelor’s degree or above
• Scientific reasoning and engineering execution
• Data structures and algorithms
• Python
• C, C++, Go, or Java
• Operating systems
• Computer networks
• Cybersecurity
• Web vulnerabilities
• OWASP Top 10
• Penetration testing
• Large-model and AI-agent architectures
• Large-model API usage
• Harness development
• Technical writing
• Chinese reading, writing, and spoken communication