- Beijing, China
Responsible for end‑side model deployment, optimization, and system integration across heterogeneous CPU/GPU/NPU environments, ensuring performance, latency, throughput, and stability balance.
Responsibilities
- Deploy end‑side models across CPU/GPU/NPU platforms
- Perform performance profiling and bottleneck analysis
- Implement token routing, device‑cloud orchestration, and low‑latency multimodal inference
- Apply quantization, speculative decoding, and on‑policy distillation techniques
- Align with Agentic OS framework metrics and establish performance regression and stability monitoring
Requirements
- Master’s degree in Artificial Intelligence, Computer Science, Electronic Information Technology or related field
