AI Performance Engineer; Cloud AI Engineering), Sr Sr

Company:
Qualcomm Technologies, Inc.

Job Area:
Engineering Group >
Machine Learning Engineering

General

Summary:

Qualcomm is utilizing its traditional strengths in digital wireless technologies to play a central role in the evolution of Cloud AI. The Qualcomm Cloud AI team is developing hardware and software solutions for Inference Acceleration.

• Convert, optimize and deploy models for efficient inference using PyTorch and ONNX.
• Work at the forefront of GenAI by understanding advanced algorithms (e.g., attention mechanisms, MoEs) and numerics to identify new optimization opportunities.
• Analyze performance and optimize LLM, VLM, and diffusion models for inference, scaling performance for throughput and latency constraints.
• Map next-generation AI workloads on top of current and future hardware designs.
• Collaborate with customers and internal compiler, firmware, and platform teams to drive solutions.
• Analyze complex performance or stability issues to determine root causes.
• Create engineering solutions that deliver continuous insights into performance of AI workloads, guiding improvements over time.
• Design and implement high-level kernels (e.g., in Triton) focused on generating efficient, low-level code.

• Hands‑on experience building and optimizing language models, notably in PyTorch and ONNX, preferably in production‑grade environments.
• Deep understanding of transformer architectures, attention mechanisms, and performance trade‑offs.
• Experience with workload‑mapping strategies exhibiting 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 work effectively in a fast‑paced, collaborative environment.
• MS in Computer Science, Machine Learning, Computer Engineering, or Electrical Engineering.

• 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 torch
  
  Dynamo.
• PhD in Computer Science, Computer Engineering, or Machine Learning.

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 6+ years of hardware, software, or systems engineering experience.
• Master's degree in Computer Science, Engineering, Information Systems, or related field and 5+ years of hardware, software, or systems engineering experience.
• PhD in Computer Science, Engineering, Information Systems, or related field and 4+ years of hardware, software, or systems engineering experience.

• Pay range: $ – $.
• Competitive annual discretionary bonus program and annual RSU grants.
• Highly competitive benefits package.

Qualcomm is an equal opportunity employer. If you are an individual with a disability and need accommodation during the application/hiring process, Qualcomm is committed to providing an accessible process and will provide reasonable accommodations to support participation.