AI Agent Platform Engineer

Binance is looking for an AI Agent Platform Engineer to join its growing AI infrastructure team. You will design and build the foundational platform components that enable AI agents to operate at scale across Binance's products and services, working at the intersection of cutting-edge AI research and high-performance systems engineering.

• Design and implement core infrastructure for AI agent deployment and orchestration
• Build scalable platforms for LLM-based agent workflows across Binance products
• Collaborate with AI researchers and product teams to translate agent capabilities into production systems
• Develop tooling for agent monitoring, evaluation, and continuous improvement
• Ensure platform reliability, performance, and security at Binance's global scale
• Contribute to architectural decisions for Binance's AI platform roadmap

• Strong software engineering background with expertise in Python and distributed systems
• Experience with LLM APIs and agent frameworks (LangChain, AutoGPT, or similar)
• Knowledge of ML infrastructure and model serving (Triton, Ray Serve, or similar)
• Familiarity with microservices architecture and cloud platforms (AWS, GCP, or Azure)
• Experience building production-grade AI systems at scale

Binance is hiring an AI Agent Platform Engineer (Openclaw) to build the infrastructure powering hundreds of AI agents across trading, compliance, customer service, risk, and beyond. Hybrid — Asia/Hong Kong (work-from-home also available).

Responsibilities: Build, publish, and maintain OpenClaw skills — modular capability units used by hundreds of agents; develop CLI tooling for agent operations (deployment, diagnostics, session management, skill registry); own end-to-end AI agent harness engineering including lifecycle management and context/session tuning; instrument the agent fleet with data pipelines and dashboards; optimize LLM infrastructure (token budgeting, multi-provider routing, cost attribution); harden agent sandboxes (credential isolation, prompt injection defense, guardrails).

Requirements: 5+ years software/platform engineering; 2+ years hands-on LLM or AI agent systems in production; AI Native mindset — defaults to AI-assisted development; skill and CLI development experience in TypeScript and/or Python; practical experience with OpenClaw, LangGraph, AutoGen, CrewAI, or equivalent orchestration runtimes; LLM infrastructure knowledge (token management, model routing); data science capability for log analysis and telemetry.