Job Description

The ByteDance Large Model Team is committed to developing the most advanced AI large model technology in the industry, becoming a world-class research team, and contributing to technological and social development. The Large Model Team has a long-term vision and determination in the field of AI, with research directions covering NLP, CV, speech, and other areas. Relying on the abundant data and computing resources of the platform, the team has continued to invest in relevant fields and has launched its own general large model, providing multi-modal capabilities.

The Machine Learning (ML) System sub-team combines system engineering and the art of machine learning to develop and maintain massively distributed ML training and inference system/services around the world, providing high-performance, highly reliable, scalable systems for LLM/AIGC/AGI.

In our team, you'll have the opportunity to build the large scale heterogeneous system integrating with GPU/NPU/RDMA/Storage and keep it running steadily and reliably, enrich your expertise in coding, performance analysis and distributed system, and be involved in the decision-making process. You'll also be part of a global team with members from the United States, China and Singapore working collaboratively towards unified project direction.

Responsibilities
- Responsible for ensuring our ML systems are operating and running efficiently for large model deployment, training, evaluation, and inference
- Responsible for the stability of offline tasks/services in multi-data center, multi-region, and multi-cloud scenarios
- Responsible for resource management and planning, cost and budget, including computing and storage resources
- Responsible for global system disaster recovery, cluster machine governance, stability of business services, resource utilisation improvement and operation efficiency improvement
- Build software tools, products and systems to monitor and manage the mL infrastructure and services efficiently
- Be part of the global team roster that ensures system and business on-call support