AI Performance Engineer, Cloud AI (Multiple Levels: Entry-Level to Senior Staff) (Hsinchu/Taipei)
Qualcomm1 month ago
Hsinchu, Taiwan or Taipei, TaiwanEntry Level / Mid Level / Senior / Staff+
Responsibilities
- Convert, optimize, and deploy models for efficient inference using PyTorch and ONNX.
- Analyze and optimize LLM, VLM, and diffusion-model inference for throughput and latency constraints.
- Study transformer algorithms, attention mechanisms, mixture-of-experts architectures, and numerical performance trade-offs.
- Map current and future AI workloads onto hardware designs using sharding and parallelism strategies.
- Collaborate with customers and internal compiler, firmware, and platform teams to develop solutions.
- Analyze complex performance and stability issues and identify root causes.
- Create engineering solutions that provide continuous performance insights for AI workloads.
- Design and implement high-level kernels, including kernels in Triton, that generate efficient low-level code.
Requirements
- 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.
- Hands-on experience building and optimizing language models, particularly with PyTorch and ONNX, preferably in production environments.
- Deep understanding of transformer architectures, attention mechanisms, and performance trade-offs.
- Experience with workload mapping strategies involving sharding or other forms of parallelism.
- Strong Python programming skills.
- Understanding of computer architecture, ML accelerators, in-memory processing, and distributed systems.
- Strong communication, problem-solving, collaboration, and learning skills.
- Preferred qualifications include knowledge of neural-network operators, linear algebra, mathematical libraries, machine-learning compilers, model accuracy evaluation, torch.compile, and torchDynamo.
- 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.