About this role

Join Zoom's AI Infrastructure team to build and optimize the core systems that power AI across our products. You will work on high-performance inference systems, focusing on latency, throughput, and cost, and contribute to cutting-edge AI advancements in real-time communication, computer vision, and natural language understanding.

What we are looking for

6

Build and tune inference serving stack for transformer and multimodal models
Implement inference optimizations like speculative decoding and continuous batching
Extend and customize inference frameworks (vLLM, SGLang, TensorRT-LLM)
Profile GPU workloads and root-cause performance regressions
Partner with researchers to bring new models into production
Contribute to on-call and production support for AI services

Skills mentioned

2

PythonC++