Senior Research Engineer for On-Device LLM Efficiency

Qualcomm, a leading technology innovator, is seeking a Senior Research Engineer to focus on On-Device LLM Efficiency. This role sits at the intersection of machine learning research and practical implementation, where you'll be pushing the boundaries of what's possible with large language models on device-constrained environments.

As a Machine Learning Researcher at Qualcomm, you'll be conducting fundamental research to create innovative machine learning methodologies that achieve beyond state-of-the-art performance. The role involves sophisticated work on LLM inference and decoding, including cutting-edge areas like speculative decoding and token-wise conditional computing.

The position requires a strong technical foundation with a Master's degree in AI, Computer Science, or related fields, coupled with 3+ years of machine learning research experience. Your day-to-day responsibilities will include researching and engineering efficient LLM solutions, implementing them in both simulated and real device environments, and contributing to research publications.

This is an excellent opportunity for someone who combines deep theoretical knowledge with practical engineering skills. The ideal candidate will have experience with Python and PyTorch, and a strong background in LLM reasoning or inference acceleration research. Those with a PhD and publication experience at major AI conferences like NeurIPS, ICML, and ICLR will be particularly well-suited for this role.

Working at Qualcomm means being at the forefront of digital transformation and helping create a smarter, connected future. You'll be part of a team that's driving innovation in on-device AI, working on solutions that will impact millions of devices worldwide. The role offers the perfect blend of academic research and practical engineering, with the opportunity to see your innovations deployed in real-world applications.