Product Manager, AI Agent & Harness

Agent Product Design: Own the design of Agent-related capabilities across Binance Agentic, including task flows, user interaction patterns, capability boundaries, failure fallbacks, and result feedback loops.

Harness & Evaluation: Build and maintain the Harness framework — design test scenarios, define evaluation criteria, curate task sets, analyze performance, and drive actionable iteration recommendations.

Cross-functional Delivery: Partner closely with Tech Owners, frontend engineers, and Skill design leads to break down business requirements into shippable, testable, production-ready product specs.

Web3 Use Case Discovery: Map high-value, deployable Agent use cases across Web3 Wallet, Account, Payment, Trading, and other Binance business lines.

Industry Tracking: Stay current on AI Agent, MCP, tool-calling, prompt engineering, and automated evaluation developments — and translate them into executable product initiatives for the team.

Metrics & Quality: Define and track Agent performance metrics, including task success rate, user satisfaction, error rate, response quality, and tool-calling accuracy.

Continuous Improvement: Proactively identify issues from real-world Agent usage and drive improvements across product, engineering, and operations.