Senior/Staff AI Performance Engineer, Cloud AI (Hsinchu/Taipei)

Teknik, data och digitalt · Data, AI och analys · Maskininlärning · Data engineering

I korthet

Qualcomm is hiring Senior/Staff AI Performance Engineers to optimize hardware and software solutions for Cloud AI, focusing on Inference Acceleration. The role involves model conversion, optimization, and performance analysis of advanced AI models like LLMs and diffusion models.

Ansvarsområden

Convert, optimize, and deploy models for efficient inference using PyTorch and ONNX.
Understand advanced algorithms (e.g., attention mechanisms, MoEs) and numerics for optimization.
Analyze and optimize LLM, VLM, and diffusion models for inference, scaling performance for throughput and latency.
Map next-generation AI workloads onto current and future hardware designs.
Collaborate with internal compiler, firmware, and platform teams, and customers to drive solutions.
Analyze complex performance or stability issues to determine root causes.
Create engineering solutions for continuous insights into AI workload performance.
Design and implement high-level kernels in Triton for efficient low-level code generation.

Krav

Hands-on experience building and optimizing language models, especially in PyTorch and ONNX, preferably in production environments.
Deep understanding of transformer architectures, attention mechanisms, and performance trade-offs.
Experience in workload mapping strategies with sharding or various parallelisms.
Strong Python programming skills.
Proactive learning about the latest inference optimization techniques.
Understanding of computer architecture, ML accelerators, in-memory processing, and distributed systems.
Strong communication, problem-solving skills, and ability to learn and work effectively in a fast-paced, collaborative environment.
MS in Computer Science, Machine Learning, Computer Engineering, or Electrical Engineering.
Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 4+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
Master's degree in Computer Science, Engineering, Information Systems, or related field and 3+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
PhD in Computer Science, Engineering, Information Systems, or related field and 2+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.

Önskade kvalifikationer

Background in neural network operators and mathematical operations, including linear algebra and math libraries.
Understanding of machine learning compilers.
Experience in converging accuracy and its evaluation methods.
Knowledge of torch.compile or torchDynamo.
PhD in Computer Science, Computer Engineering, or Machine Learning.

Förmåner

Qualcomm is an equal opportunity employer.
Qualcomm is committed to providing an accessible process for individuals with disabilities.
Qualcomm is committed to making its workplace accessible for individuals with disabilities.