AI产品工程师（安全方向） - 安全与风控
Core
Designing guardrail systems and security capabilities to enable safe deployment of Large Language Models (LLMs) for enterprise clients, mitigating risks like prompt injection and data leakage.
Role type
Product Engineer (AI Security)
Builds
Real-time guardrail systems for LLM safety
Domain
Cloud Security / AI Safety
Deliverable
production ML models
Required skills
LLM orchestration (LangChain, LlamaIndex), vector database application, classification system tuning, Python, Rust, Go, high-concurrency system design, distributed architecture, adversarial attack detection
Preferred skills
OWASP Top 10 for LLMs, cybersecurity experience, translating AI safety research into product features
Responsibilities
Collaborate with CTOs and CISOs to identify core security pain points; Develop real-time guardrail systems to detect and mitigate adversarial attacks; Optimize classification systems for security tasks; Integrate latest AI safety research into product functionality