AI Performance Engineer, Cloud AI (Multiple Levels: Entry-Level to Senior Staff) (Hsinchu/Taipei)
Qualcomm17 days ago
Hsinchu, Taiwan or Taipei, TaiwanEntry Level / Mid Level / Senior / Staff+
Responsibilities
- Convert, optimize, and deploy AI models for efficient inference using PyTorch and ONNX.
- Analyze and optimize LLM, VLM, and diffusion-model performance for throughput and latency.
- Study transformer architectures, attention mechanisms, mixture-of-experts approaches, numerics, and inference optimization opportunities.
- Map current and future AI workloads to hardware designs using sharding and other parallelism strategies.
- Collaborate with customers and internal compiler, firmware, and platform teams to develop solutions.
- Diagnose complex performance and stability issues and identify root causes.
- Create engineering solutions that provide continuous insights into AI workload performance.
- Design and implement high-level kernels, including Triton kernels, that generate efficient low-level code.
Requirements
- Hands-on experience building and optimizing language models with PyTorch and ONNX, preferably in production environments.
- Strong Python programming skills and a deep understanding of transformer architectures, attention mechanisms, and performance trade-offs.
- Experience with workload mapping strategies involving sharding or other forms of parallelism.
- Understanding of computer architecture, ML accelerators, in-memory processing, and distributed systems.
- Bachelor’s degree in Computer Science, Engineering, Information Systems, or a related field plus 4+ years of relevant experience; or a master’s degree plus 3+ years; or a PhD plus 2+ years.
- Knowledge of neural network operators, linear algebra, mathematical operations, and math libraries is a bonus.
- Understanding of machine learning compilers, model-accuracy convergence and evaluation methods, torch.compile, or torchDynamo is a bonus.
- A PhD in Computer Science, Computer Engineering, or Machine Learning is a bonus.
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.