
AI Infrastructure Software Engineer
AI
Build and architect a production-grade Agent Infra platform supporting enterprise AI Agents, covering model invocation, RAG, orchestration, memory, evaluation, and observability. Requires strong backend engineering skills in Python, Go, Java, or TypeScript, plus LLM/RAG and observability experience. Fluent Chinese and English required.
What you'll do
- Lead architectural design and engineering of the Agent Infra platform, covering model gateway, Agent Runtime, workflow orchestration, tool execution, sandboxing, state memory, evaluation, and observability
- Build a unified model invocation layer with OpenAI-compatible APIs, model routing, fallbacks, rate limiting, token metering, caching, and cost attribution
- Design and optimize the RAG data and knowledge layer including document parsing, chunking, embedding, vector search, re-ranking, and retrieval pipeline tuning
What you need
Must-have
PythonGoJavaTypeScriptLLM application developmentAgent frameworksWorkflow frameworksRAG
Nice-to-have
LangSmithLangfuseHeliconeMCPE2BModalPlaywrightPuppeteer
Soft skills
Security and governance mindsetProblem decomposition under uncertaintyRapid validation of ideasCross-functional collaboration
AI InfrastructureAgent InfraLLMRAGObservabilityBackend EngineeringDistributed SystemsEntertainmentFull-timeRemote