Large Language Model Inference System Engineer Graduate (Applied Machine Learning) - 2027 Start
Summary
Build and optimize distributed inference systems for large language models, focusing on performance, cost, and multi-tenant stability.
- Build disaggregated multi role inference systems
- Design heterogeneous inference pipelines
- Develop machine learning inference systems
- Enable elastic computing for inference
- Implement distributed KV cache systems
- Improve inference stability
- Optimize large model inference performance
- Reduce large model inference cost
- Support multi tenant co located inference