Scholar
Prathamesh Mandke
Google Scholar ID: wB6ZbbMAAAAJ
Sr Machine Learning Engineer at Qualcomm AI Research
Citations & Impact
Citations
30
H-index
2
i10-index
1
Publications
7
Co-authors
0
Contact
Resume (English only)
Academic Achievements
- Implemented Qualcomm's first LLM LoRA fine-tuning on Snapdragon mobile CPU using PyTorch in C++; Co-developed a Federated Learning SDK with MSFT Research; Demonstrated end-to-end SW for Federated and On-Device Personalization R&D at NeurIPS'21 and NeurIPS'23; Published work at Interspeech'23.
Research Experience
- Worked as a Software Engineer Intern at Qualcomm, developing visualization utilities for AIMET features; Graduate Research Assistant at Virginia Tech, working on sparse view CT image reconstruction using deep Convolution Neural Networks; Summer Intern at Flytbase, Inc., working on deep learning-based barcode localization in warehouse automation; Intern at Siemens, Ltd., designing and building a contactor testing fixture automaton.
Education
- Master's degree in Computer Engineering from Virginia Tech, GPA: 4.0/4.0; Bachelor of Technology in Electronics and Telecommunication from College of Engineering, Pune (COEP), GPA: 9.11/10. Advisor: Prof. Anuj Karpatne.
Background
- Currently a Senior ML Engineer at Qualcomm AI Research, focusing on on-device personalization and adaptation of Large Language and Vision Models. During his Master's at Virginia Tech, he worked with Prof. Anuj Karpatne in the Dept. of CS on using domain-specific prior knowledge in machine learning to accelerate scientific discovery. Enjoys writing code in Python and C++.
Miscellany
- In his free time, he loves to play soccer, take road trips, and play the keyboard.
Co-authors