ML Scheduler Engineer: Optimizing GPU/CPU Orchestration

ByteDance; San Jose (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

ByteDance's Volcano Ark team is seeking a software engineer to design and develop resource scheduling systems for machine learning workloads across data centers and clusters. The role involves optimizing orchestration of GPUs, CPUs, storage, and networking to support offline training and online inference.

The candidate should have a CS degree, strong programming skills (Go/Java/Python), experience with ML frameworks (TensorFlow/PyTorch), and solid knowledge of Kubernetes, Docker, and distributed

Qualifications

• Bachelor's or Master's degree in Computer Science or a related discipline.
• Proficient in one or two programming languages in a Linux environment, such as Go, Java, or Python.
• Solid foundation in algorithms, data structures, and good coding habits.
• Familiar with at least one mainstream ML framework (TensorFlow, PyTorch).
• Familiar with Kubernetes architecture and container tech (Docker, container, Kata).
• Understands distributed systems and has worked on large-scale distributed systems.

Responsibilities

• Design and develop resource scheduling systems for ML workloads across Volcano Ark and ML platform products.
• Optimize orchestration and scheduling of GPUs, CPUs, storage, and network resources across data centers and clusters.
• Support offline training, online inference, and other workloads with multi-tenant isolation to improve utilization and efficiency.

Skills

Go

Java

Python

Linux

Distributed systems

Kubernetes

Docker

TensorFlow

PyTorch

Education

Bachelor's degree in Computer Science or related

Tools

Docker

Kubernetes

Job description

ByteDance's Volcano Ark team is seeking a software engineer to design and develop resource scheduling systems for machine learning workloads across data centers and clusters. The role involves optimizing orchestration of GPUs, CPUs, storage, and networking to support offline training and online inference.

The candidate should have a CS degree, strong programming skills (Go/Java/Python), experience with ML frameworks (TensorFlow/PyTorch), and solid knowledge of Kubernetes, Docker, and distributed