Senior Staff Deep Learning Researcher – Model Efficiency - Qualcomm - Amsterdam
Core
Conducting fundamental research to optimize Large Language Models (LLMs) and Large Vision Models (LVMs) for on-device efficiency, focusing on quantization, compression, and efficient data types.
Role type
Senior Staff Deep Learning Researcher (Model Efficiency)
Builds
Novel techniques for model quantization, compression, and efficient inference for edge devices and data centers.
Domain
Artificial Intelligence / Deep Learning / Model Optimization
Deliverable
production ML models
Required skills
Deep learning research, model quantization, model compression, efficient data types, conditional compute, inference time compute, research roadmap definition, mentoring, cross-functional collaboration, academic publishing
Preferred skills
Publications in top-tier conferences (NeurIPS, ICML, ICLR, CVPR), experience with hardware accelerators, industrial research leadership
Technologies
LLMs, LVMs, quantization frameworks, compression algorithms
Responsibilities
Design and implement novel solutions for inference efficiency, mentor team members and define research roadmaps, publish research findings in top-tier conferences, collaborate with cross-functional teams to deploy models on devices.
Seniority
Senior Staff, hands-on IC with mentorship
