- Beijing, Beijing, China
- Senior
- 2+ years
The Data Center Customer Engineering team is seeking a Cloud AI Senior Engineer to support deployment and customer enablement of AI and generative AI workloads on Qualcomm Cloud AI accelerators.
Responsibilities
- Deploy, integrate, and validate AI/ML and LLM inference workloads on Qualcomm Cloud AI accelerator platforms.
- Support customer model onboarding, environment setup, functional validation, basic performance, and issue reproduction.
- Work with AI frameworks, model conversion/deployment flows, runtime APIs, and accelerator software stacks to enable customer use cases.
- Debug software issues across applications, frameworks, runtime, drivers, operating system, and platform interfaces; collect logs and traces and drive clear issue reports.
- Perform basic LLM performance analysis using metrics such as latency, throughput, tokens/second, Time to First Token (TTFT), and resource utilization; escalate deep optimization topics to specialist teams when appropriate.
Requirements
- Master’s degree in Computer Science
- Electrical/Computer Engineering
- Software Engineering, or a related technical discipline
- PhD
- Nice to have: LLM kernel optimization