Cloud AI Inference Performance Engineer

Qualcomm; Cork; On-site; EUR 90,000 - 150,000; Full time

Benefits offered by this job

Stock options

Performance bonus

Relocation assistance

Education assistance

Pension & Life Insurance

Wellbeing subsidies

Employee clubs

Job summary

Qualcomm is expanding its Cloud AI Engineering team in Cork, Ireland, seeking AI Performance Engineers to optimize inference for LLMs, VLMs, and diffusion models. You will deploy models, explore GenAI workloads, and collaborate with compiler and platform teams to improve performance across devices.

The role covers research to deployment, with emphasis on architecture understanding, software optimization, and strong communication in a fast-paced, global environment.

Qualifications

• Bachelor's degree with 4+ years software engineering experience or
• Master's with 3+ years software experience or
• PhD with 2+ years software experience

Responsibilities

• Convert, optimize and deploy models for inference using PyTorch and ONNX.
• Explore GenAI workloads and optimization opportunities.
• Analyze performance and optimize LLM, VLM, and diffusion models for throughput and latency.

Skills

Python programming

Transformer models

PyTorch

ONNX

Performance optimization

Strong communication

C/C++

Education

Master's degree in CS/ML/CE/EE

PhD in CS/CE/ML

Bachelor's degree in Engineering/CS/related

Tools

Triton

Job description

Qualcomm is expanding its Cloud AI Engineering team in Cork, Ireland, seeking AI Performance Engineers to optimize inference for LLMs, VLMs, and diffusion models. You will deploy models, explore GenAI workloads, and collaborate with compiler and platform teams to improve performance across devices.

The role covers research to deployment, with emphasis on architecture understanding, software optimization, and strong communication in a fast-paced, global environment.