Product Manager, AI Agent & Harness
New
B
BinanceAI and Web3
Location: Hong Kong; SingaporeFull-TimeManager
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Strong English reading and writing skills
- Required Skills
- Content managementPrompt Engineering
Requirements
- Experience in AI products, Agent products, AIGC applications, automation tools, or developer tooling.
- Background in Web3, exchanges, wallets, payments, on-chain transactions, DeFi, or crypto assets.
- Hands-on understanding of AI Agent tool-calling, task planning, context management, and evaluation frameworks.
- Ability to define problems, decompose workstreams, and drive execution in ambiguous environments.
- Ability to produce clear PRDs, flow diagrams, test cases, acceptance criteria, and iteration plans.
- Collaborate across engineering, design, operations, and business stakeholders.
- Bonus: Experience with exchanges, Web3 wallets, on-chain trading, payments, or fintech products.
- Bonus: Experience with AI Agent Harness, Eval, benchmarking, automated testing platforms, or prompt evaluation.
- Bonus: Familiarity with MCP, Function Calling, RAG, multi-Agent orchestration, or workflow automation.
- Bonus: Knowledge of the Binance ecosystem or mainstream Web3 user scenarios.
- Bonus: Strong English reading and writing skills.
Responsibilities
- Design Agent capabilities, task flows, user interaction patterns, capability boundaries, failure fallbacks, and result feedback loops.
- Build and maintain the Harness framework by designing test scenarios, defining evaluation criteria, and curating task sets.
- Analyze Agent performance and recommend actionable iterations.
- Work with Tech Owners, frontend engineers, and Skill design leads to turn business requirements into shippable, testable product specifications.
- Identify deployable Agent use cases across Web3 Wallet, Account, Payment, Trading, and other Binance business lines.
- Track developments in AI Agents, MCP, tool-calling, prompt engineering, and automated evaluation, and translate them into product initiatives.
- Define and track task success, user satisfaction, error rate, response quality, and tool-calling accuracy metrics.
- Identify issues from real-world Agent usage and drive improvements across product, engineering, and operations.
View Full Description & ApplyYou'll be redirected to the employer's site
