Sai Gokhale

Operations Associate

United States2 yrs 6 mos experience

Most Likely To Switch

Key Highlights

Focused on efficient and data-efficient ML.
Interned at AMD optimizing LLMs for Ryzen AI.
Graduate Teaching Assistant at Georgia Tech.

Stackforce AI infers this person is a Machine Learning Engineer with a focus on model optimization and inference efficiency.

Contact

saigokhale2002@gmail.com LinkedIn

Skills

Core Skills

Model OptimizationInference Efficiency

Other Skills

chunked prefillKV cache quantizationweight-only LLM quantization

About

Hi! I’m currently an MS CS student at Georgia Tech, focusing on efficient and data-efficient ML. I was interning at AMD, working on model optimization for LLMs to improve inference efficiency on Ryzen AI hardware. Previously, I worked as an MTS at Oracle, contributing to their cloud platform. I’d love to connect and chat if you share interests in ML systems and applied research. I’m also exploring full-time opportunities starting May 2026.

Experience

2 yrs 6 mos

Total Experience

1 yr 3 mos

Average Tenure

1 yr 5 mos

Current Experience

Georgia institute of technology

3 roles

Graduate Teaching Assistant

Jan 2026 – Present · 5 mos

Graduate Student Researcher

Jan 2025 – Present · 1 yr 5 mos

Working on Knowledge Distillation with Vision-Language Models (VLMs) for efficient labeling at DML Lab, Georgia Tech, under the supervision of Dr. Stephen Mussmann.

Graduate Teaching Assistant

Jan 2025 – May 2025 · 4 mos

Course - CSE 6242: Data & Visual Analytics

Amd

SDE AI intern

May 2025 – Dec 2025 · 7 mos · San Jose, California, United States · On-site

Working on model optimization techniques to improve inference efficiency on Ryzen AI NPUs. Implemented and evaluated chunked prefill, KV cache quantization, and weight-only LLM quantization strategies, enabling efficient long-context inference.

model optimizationinference efficiencychunked prefillKV cache quantizationweight-only LLM quantization