AI Researcher, On-Device LLM Efficiency

Responsibilities

• Conduct research and development in LLM inference efficiency algorithms and efficient model architecture design
• Develop creative machine learning solutions while considering practical challenges for on-device deployment
• Implement and evaluate proposed solutions in both simulation and on-device environments
• Collaborate with cross-functional teams to enhance mobile, edge, automotive, and IoT products

Requirements

• Master's degree in Computer Engineering, Computer Science, Electrical Engineering, or a related field
• 4+ years of AI research experience
• Strong background in deep learning and Transformer architectures
• Proficiency in Python and PyTorch
• Experience in LLM reasoning or inference acceleration research

Preferred Qualifications

• PhD in Computer Science, Electrical Engineering, or a related field
• Research experience in LLM efficiency, such as efficient attention, inference acceleration, or KV cache compression
• Experience with on-device AI deployment on mobile or edge devices
• Proven track record of publishing research at top-tier AI/ML conferences (e.g., NeurIPS, ICML, ICLR) as a lead author

About the Company

Qualcomm is a leading technology innovator that pushes the boundaries of possibility to enable next-generation experiences. We drive digital transformation to help create a smarter, connected future for all through breakthrough technologies in mobile, edge, auto, and IoT.