实时互动后台研发工程师
Core
Design and develop high-concurrency scheduling systems for real-time interactive backend services, optimize GPU inference engineering, and build data platforms.
Role type
Senior backend engineer (high-concurrency & GPU inference)
Builds
High-availability task scheduling systems, GPU inference services, and data processing pipelines
Domain
Real-time interactive services, cloud-native infrastructure, heterogeneous compute
Deliverable
production ML models
Required skills
High-concurrency distributed systems, GPU inference optimization, cloud-native technologies, multi-tenant architecture, system observability, AI coding tools
Preferred skills
Heterogeneous resource scheduling, complex system design, cross-team collaboration
Technologies
Distributed task schedulers, message queues, caching middleware, AI coding agents
Responsibilities
Design high-concurrency scheduling systems for core business tasks; Engineer and optimize GPU inference services for low latency; Build and optimize data platforms; Lead observability体系建设 and troubleshoot production issues; Collaborate on complex system delivery and adopt AI tools to improve efficiency.