c
contib5

Sarthak S

@contib5

ML Engineer, model compression and FPGA inference

Singapore
English
About me
I build fast, efficient deep learning systems. I quantize and compress PyTorch models, turn neural networks into FPGA designs with Vivado, and run and debug large GPU training jobs. I can speed up your model, shrink it for edge devices, or get it running on hardware, with clear reports and reproducible code.... Read more

Skills

c
contib5
Sarthak S
Offline • 

See my services

AI Implementation & Deployment
I will quantize and compress your pytorch model for faster inference
Custom Websites
I will build a fast, responsive website or landing page