AI Performance Engineer (Cloud AI Engineering), Sr | Staff | Sr. Staff

Stack

Responsibilities

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

Requirements

• ▹Bachelor's degree in Computer Science, Engineering, Information Systems or related field and 6+ years of experience (or Master's + 5 years, or PhD + 4 years).
• ▹MS in Computer Science, Machine Learning, Computer Engineering or Electrical Engineering.

Nice to have

• ▹Hands-on experience building and optimizing language models, notably in PyTorch and ONNX, preferably in production.
• ▹Deep understanding of transformer architectures, attention mechanisms and performance tradeoffs.
• ▹Experience with workload mapping strategies such as sharding or parallelism.
• ▹Strong Python programming skills.
• ▹Understanding of computer architecture, ML accelerators, in-memory processing and distributed systems.
• ▹Background in neural network operators and math fundamentals (linear algebra, math libraries).
• ▹Understanding of machine learning compilers.
• ▹Experience with accuracy convergence and its evaluation methods.
• ▹Knowledge of torch.compile or torchDynamo.
• ▹PhD in Computer Science, Computer Engineering or Machine Learning.

Soft skills

What we offer

• ▹Annual discretionary bonus program.
• ▹Annual RSU grants.
• ▹Competitive benefits package.

About the company

Qualcomm is applying its traditional strengths in digital wireless technology to play a central role in the evolution of Cloud AI, developing hardware and software solutions for inference acceleration.