AI Researcher, On-Device LLM Efficiency

Stack

Responsibilities

• ▹Research and development in LLM inference efficiency algorithms, efficient model architecture design, and/or LLM training
• ▹Develop creative solutions with consideration of practical challenges on devices
• ▹Implement and evaluate possible solutions in both simulation and on-device environments

Requirements

• ▹Master's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field
• ▹6+ months of academic and/or work experience developing/optimizing machine learning models, systems, platforms, or methods
• ▹4+ years of AI research experience
• ▹Strong background in deep learning and Transformers
• ▹Strong programming skills in Python and PyTorch
• ▹Experience in LLM reasoning or inference acceleration research

Nice to have

• ▹PhD in Computer Science, Electrical Engineering, or related field
• ▹Experience in LLM efficiency research such as efficient attention, inference acceleration, or KV cache compression
• ▹Experience in on-device AI deployment on mobile or edge devices
• ▹Publishing research papers at top-tier AI/ML conferences (NeurIPS, ICML, ICLR) as lead author

Soft skills

What we offer

• ▹Annual discretionary bonus program
• ▹Opportunity for annual RSU grants
• ▹Highly competitive benefits package
• ▹Indicative pay range: $138,800–$208,200

About the company

Qualcomm Technologies, Inc. is a leading technology innovator advancing mobile, edge, automotive and IoT products through machine learning research.