Shubham Deshmukh is a Staff Engineer based in Bengaluru with 10 years of experience specializing in high-performance AI systems for LLM inference and optimization. He focuses on transformer-level improvements, CXL-backed memory scaling, and low-latency inference serving via distributed pipelines, bringing research-grade rigor to production challenges. Currently at Samsung Semiconductor after progressing from Associate Staff Engineer there, he has prior NLP engineering experience and a strong foundation in computer engineering. He holds an MTech in DS and Engineering from BITS and maintains an academic footprint visible on Google Scholar, indicating ongoing research contributions. Known for bridging systems engineering with model-level optimizations, he excels at squeezing more throughput and memory efficiency from modern inference stacks. Colleagues value his mix of practical deployment experience and deep technical curiosity about emerging memory and inference architectures.
10 years of coding experience
4 years of employment as a software developer
Master of Technology - MTech, DS and Engineering, Master of Technology - MTech, DS and Engineering at BITS
Diploma, Computer Engineering, Diploma, Computer Engineering at MSBTE
Bachelor's degree, Computer Engineering, Bachelor's degree, Computer Engineering at Savitribai Phule Pune University
Contributions:26 commits, 23 pushes, 1 branch in 2 years 6 months
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.