AI Agent Platform Engineer (Openclaw)

Binance is building one of the largest internal AI agent fleets in the industry — hundreds of sandboxed agents powering automation across trading, compliance, customer service, risk, and beyond. This role sits at the core of that platform: you'll build the infrastructure and tooling that makes every agent faster, smarter, and more impactful — directly translating into operational efficiency gains and accelerating business growth.

We're looking for a strong individual contributor who stays close to the frontier and has the instinct to turn promising ideas into working implementations.

This is a builder role. You'll own the full stack from agent skill authorship to infrastructure tuning, and you'll be the person who spots a new technique in the wild and figures out how to make it real inside our platform.

Responsibilities

• Build, publish, and maintain OpenClaw skills — modular capability units used by hundreds of agents across the org to automate repetitive work and unlock new business capabilities

  
  

• Develop CLI tooling for agent operations: deployment, diagnostics, session management, skill registry, and developer workflows

  
  

• Own end-to-end AI agent harness engineering: lifecycle management, tool execution, context/session tuning, compaction strategies, model routing

  
  

• Instrument the agent fleet with data pipelines and dashboards; apply data science techniques to understand token efficiency, failure modes, latency distribution, and business outcome correlation

  
  

• Identify bottlenecks across the platform and drive measurable improvements in agent throughput, response quality, and cost efficiency — directly supporting user growth and retention

  
  

• Track the research frontier — papers, open-source releases, community developments — and rapidly prototype integrations (new model capabilities, reasoning techniques, agentic frameworks)

  
  

• Optimize LLM infrastructure: token budgeting, multi-provider routing, cost attribution, context window management

  
  

• Harden agent sandboxes: credential isolation, prompt injection defense, guardrails

  
  

• Partner with product and business teams to translate user growth goals into reliable, scalable agent workflows

  
  
  

Requirements

• 5+ years in software/platform engineering; 2+ year hands-on with LLM or AI agent systems in production

  
  

• AI Native mindset — you default to AI-assisted development, think natively in agent/tool/context primitives, and are allergic to doing manually what an agent could do

  
  

• Skill & CLI development: experience building modular, composable tools or CLI utilities for developer platforms; TypeScript and/or Python fluency

  
  

• Agent harness engineering: practical experience with OpenClaw, LangGraph, AutoGen, CrewAI, or equivalent orchestration runtimes

  
  

• LLM infrastructure: token management, model routing, context compaction, cost optimization at scale

  
  

• Data science capability: comfortable with log analysis, statistical profiling, SQL/Python for usage data; can translate raw telemetry into actionable insights that drive platform decisions

  
  

• Research awareness: follows model releases, agent framework updates, and relevant literature; can quickly assess what's worth integrating and what isn't

  
  

• Vibe coding: ships fast using AI-assisted workflows; iterative, pragmatic, high output-to-noise ratio with strong engineering fundamentals

  
  
  

Nice to have

• Direct experience with OpenClaw — session config, hooks, cron/heartbeat architecture, skill registry (ClawHub)

  
  

• Familiarity with CLI (Command Line Interface) and the agent tooling ecosystem

  
  

• LiteLLM / AWS Bedrock / multi-provider proxy experience

  
  

• Kubernetes/EKS: pod isolation, resource tuning, secrets management

  
  

• Security engineering background: sandbox escapes, prompt injection, guardrail design