Levin Dabhi
Machine Learning Compiler Engineer at Qualcomm
Cork, Ireland
Summary
👤
Senior🎓
Top SchoolLevin Dabhi is a Machine Learning Compiler Engineer with eight years of experience optimizing AI workloads for GPUs and specialized accelerators, currently driving compiler and kernel performance at Qualcomm. He has a proven track record building high-performance deep learning kernels and compiler passes (operator splitting, graph partitioning) at Intel and startups, focused on squeezing maximum throughput and efficiency from hardware. Comfortable with C++, Python, and MLIR-based compiler infrastructure, Levin bridges low-level performance engineering with practical model deployment needs for both training and inference. His background spans R&D for low-power accelerators, computer vision projects (high-res virtual try-on and background removal), and robotics reinforcement learning, giving him a broad systems-and-ML perspective. Based in Cork, Ireland, he publishes work and code on GitHub and maintains a personal site showcasing his applied research and tools for AI hardware acceleration.
8 years of coding experience
6 years of employment as a software developer
Bachelor of Technology - BTech Computer Science, Bachelor of Technology - BTech Computer Science at Nirma University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (76)
stylegan10
deep-q-network10
image-quality10
siggraph9
openai-gym9
image-matching9
nlp9
q-learning9
style-transfer9
python9
generative-adversarial-network9
pytorch9
keras9
try-on9
deep-reinforcement-learning8
Programming languages (5)
Github contributions (5)
levindabhi/SieveNet
Sep 2020 - Jun 2021
This is the unofficial implementation of SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On
Contributions:29 commits, 3 PRs, 7 pushes in 8 months
virtual-try-onobject-detectioncomputer-visionre-identificationimage-matching
levindabhi/U-2-Net
Nov 2020 - Jun 2021
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Contributions:8 commits, 2 PRs, 8 pushes in 7 months
pytorchsalient-object-detectiondeep-learningdeeperrecognition
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.