Senior/Staff AI Performance Engineer: Inference Optimization

Qualcomm; San Diego (CA); On-site; USD 178,400 - 267,600; Full time

Benefits offered by this job

Competitive annual discretionary bonus

RSU grants

Highly competitive benefits package

Job summary

Qualcomm in San Diego is looking for an AI Engineer specializing in machine learning. You will convert and optimize models, analyze performance, and collaborate across teams to advance AI technologies.

The ideal candidate should have extensive hands-on experience with PyTorch and ONNX, deep knowledge of transformer architectures, and a relevant master's or PhD degree. This position offers a competitive salary and benefits package.

Qualifications

• 6+ years of engineering experience with relevant degrees.
• Hands-on experience in production-grade environments.
• Deep understanding of performance trade-offs.

Responsibilities

• Convert, optimize, and deploy models for inference.
• Analyze performance of AI workloads.
• Collaborate with teams to drive solutions.

Skills

Building and optimizing language models

Python programming

Understanding transformer architectures

Machine learning compilers

Problem-solving skills

Education

MS in Computer Science or related field

PhD in Computer Science or related field

Tools

PyTorch

ONNX

Job description

Qualcomm in San Diego is looking for an AI Engineer specializing in machine learning. You will convert and optimize models, analyze performance, and collaborate across teams to advance AI technologies.

The ideal candidate should have extensive hands-on experience with PyTorch and ONNX, deep knowledge of transformer architectures, and a relevant master's or PhD degree. This position offers a competitive salary and benefits package.