Graduate Cloud-Native AI Inference Engineer

ByteDance’s Inference Infrastructure team is hiring engineers to design and operate cloud-native, GPU-accelerated ML platforms at scale. You will work on open-source oriented systems for large-scale LLM inference, contributing to scheduling, resource management, and GPU orchestration in a hyper-scale environment.

We seek PhD graduates with strong distributed systems knowledge, experience with Docker/Kubernetes, and proficiency in Go, Rust, Python, or C++.