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

Qualcomm

San Diego, CA, United States

1 day ago

Apply on www.juju.com

Prepare application

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Expert

Experience required

4 years minimum

Working hours

Regular working hours

Job source

www.juju.com

Tech stack

Artificial Intelligence Algorithm Design Systems Engineering Artificial Neural Networks Information Systems Computer Engineering Distributed Systems Firmware Hardware Design Python (Programming Language) Machine Learning Language Modeling

+9 more

Performance Tuning Pytorch Large Language Models AI Platforms Attention Mechanisms Information Technology ONNX (Open Neural Network Exchange) Format Transformer Architectures Machine Learning Operations

Job description

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.

Requirements

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 torchDynamo.
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.

Benefits & conditions

Pay range: $178,400.00 - $267,600.00.
Competitive annual discretionary bonus program and annual RSU grants.
Highly competitive benefits package.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.juju.com

Prepare application

Good distractions

Loading talks and stories from around this role…