3 days ago
Shanghai, China or Beijing, ChinaSenior
Responsibilities
- Develop and optimize AI kernels and operators for Qualcomm Cloud AI platforms.
- Enable and optimize LLM, MoE, and multimodal models for large-scale cloud inference.
- Drive accuracy, performance, and efficiency improvements across the software stack.
- Improve model memory footprint and ROM/RAM efficiency through kernel, graph, and compiler optimizations.
- Collaborate with performance and modeling teams to deliver efficient inference solutions.
- Analyze and resolve performance bottlenecks using profiling, benchmarking, and modeling methods.
Requirements
- A bachelor's degree, master's degree, or PhD in Engineering, Information Systems, Computer Science, Artificial Intelligence, Mathematics, Electrical Engineering, or a related field, depending on the experience pathway.
- At least 5 years of experience in Cloud AI inference, kernel/operator development, or AI compiler technologies; the minimum qualification pathways specify 4+ years with a bachelor's degree, 3+ with a master's degree, or 2+ with a PhD.
- At least 2 years of programming-language experience with C, C++, Java, Python, or similar languages.
- Proficiency in C++, Python, and Linux development environments.
- Deep understanding of Transformer architectures, including LLMs, MoE, and modern foundation models.
- Strong experience with compiler technologies such as MLIR, Triton, or TVM, including graph transformation, operator lowering, scheduling, operator fusion, kernel auto-tuning, code generation, and memory scheduling.
- Strong experience with parallel computing architectures and performance techniques including vectorization, tiling, memory hierarchy optimization, and workload scheduling.
- Experience with graph optimization, model accuracy validation, performance optimization, and memory optimization.
- Good verbal and written English communication skills for collaboration across global teams.
- Preferred experience optimizing Attention, FlashAttention, KV Cache, Embedding, GEMM, Softmax, and MoE routing operators.
- Preferred hands-on experience developing custom operators and high-performance kernels manually or through compiler frameworks on GPUs, NPUs, TPUs, or custom AI hardware.
Categories
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.