Skip to main content
Hemanth KothapalliHK
Looking for a job

Hemanth Kothapalli

@hemanthkothapalli

ML infrastructure engineer at Qualcomm enabling Qwen3 LLM and VLM inference, with a +67% token-generation-rate finding.

India
Message

At Qualcomm AISW, I’m the single owner of Qwen3-30B MoE and Qwen3 VLM model enablement for on-device inference. I’ve driven release and validation pipelines across SoC targets, and my analysis of SS LLaMA 3.1 8B surfaced a +67% token-generation-rate improvement that triggered a production re-baseline decision.

I also built a YAML schema-migration toolchain that converted 200,000+ legacy test configurations, and enabled 140 TorchScript model variants for the QNN runtime. Earlier, I built Xlog Analytics, a Django and JavaScript tool for analyzing AI framework error logs, during my Qualcomm AISW internship.

Experience

Work history, roles, and key accomplishments

Qualcomm logoQU
Current

Senior Engineer — ML Infra & LLM Inference

Jul 2023 - Present (3 years 4 months)

Single owner of model enablement for Qwen3-30B MoE LLM inference across 3 SoC families, including quantization and release-validation pipelines. Surfaced a +67% TGR performance finding that drove a production re-baseline decision.

PythonC C++PyTorchOnnx
TorchScript
Post Training Quantization
Inference Optimization
LLM MoE VLM Architectures
JenkinsCI CDArgo
MLPerf
Procyon
GitLinux
Qualcomm logoQU

Software Engineering Intern — Full Stack

May 2022 - Jul 2022 (2 months)

Built Xlog Analytics, a Django + JavaScript internal tool for structured analysis and debugging of AI framework error logs. Delivered end-to-end from design through internal rollout in 2 months.

Education

Degrees, certifications, and relevant coursework

Indian Institute of Technology, Hyderabad logoIH

Indian Institute of Technology, Hyderabad

B.Tech, Computer Science & Engineering

Grade: 8.59/10

Activities and societies: VAK UG Research Excellence Award (2023); Elected Class Representative, CS Department.

B.Tech in Computer Science & Engineering with a CGPA of 8.59/10. Awarded the VAK UG Research Excellence Award and elected Class Representative.

Availability

Looking for a job

Location

India

Authorized to work in

Salary expectations

62k+ USD

Skills

On Device Inference
LLM Inference
VLM
MOE
Model Enablement
Post Training Quantization
Inference OptimizationRelease ValidationCI CDBenchmarking
MLPerf
Procyon
PythonCC++

Interested in hiring Hemanth?

You can contact Hemanth and 600K+ other talented remote workers on Himalayas.

Message Hemanth

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan