Shubham Gupta

Sunnyvale, California

My specialty is Edge AI: running large language models on small devices.

I work at Amazon Lab126, where I build and ship LLM systems for smart vehicles, with demos showcased at CES 2025 and CES 2026. Alongside engineering, I am actively involved in research. I have presented posters at the Stanford Graph Learning Workshop and at MLSys, and published at the ACM Symposium on Applied Computing. Earlier, I was a research associate at the Precog lab at IIIT Delhi and a summer student at CERN Openlab.

I hold a Master of Science in Information Security from Carnegie Mellon University. You can find more about my work on the publications, projects, and CV pages.

selected publications

Stanford
Running Large Models on Small (Edge) Devices

Shubham Gupta

2025

Abs Bib

Inference optimization for model deployment on edge devices. Explores methods such as custom KV caching, speculative decoding, mixed-precision quantization, and quantization-aware training, and how they increase accuracy and token generation throughput for edge LLMs.
@misc{gupta2025edgellms, title = {Running Large Models on Small (Edge) Devices}, author = {Gupta, Shubham}, year = {2025}, howpublished = {Poster, Stanford Graph Learning Workshop}, }
MLSys
Speciesism in the Assistant Axis: Probing Compassion Vectors in Post-Trained LLMs

Shubham Gupta and Jasmine Brazilek

2026

Abs Bib Website

Extracted assistant, human-compassion and animal-compassion persona vectors from Qwen3-32B served with vLLM on 4xL40S GPUs. Projected activations onto these axes and quantified speciesism between human and animal compassion.
@misc{gupta2026speciesism, title = {Speciesism in the Assistant Axis: Probing Compassion Vectors in Post-Trained LLMs}, author = {Gupta, Shubham and Brazilek, Jasmine}, year = {2026}, howpublished = {Poster, MLSys Young Professionals Symposium}, }

ACM SAC

Investigation of Biases in Identity Linkage Datasets

Rishabh Kaushal, Shubham Gupta, and Ponnurangam Kumaraguru

In Proceedings of the 35th Annual ACM Symposium on Applied Computing (SAC ’20), 2020

Abs DOI Bib HTML

@inproceedings{gupta2020identitylinkage,
  title = {Investigation of Biases in Identity Linkage Datasets},
  author = {Kaushal, Rishabh and Gupta, Shubham and Kumaraguru, Ponnurangam},
  booktitle = {Proceedings of the 35th Annual ACM Symposium on Applied Computing (SAC '20)},
  pages = {1861--1868},
  year = {2020},
  publisher = {ACM},
  doi = {10.1145/3341105.3374015},
}