---
title: "Gaurav Goswami - Machine Learning Engineer in Bengaluru | Tal"
description: "Meet Gaurav Goswami, ML Engineer @ Red Hat | VLMs & LLMs | Quantization (GPTQ/AWQ) | vLLM | PyTorch | Edge AI based in Bengaluru. AI stack includes claude, codex, and cursor. Explore public work links including github, leetcode, and codeforces."
image: "https://tal.club/meet/gourav-goswami/share-image"
---

# Gaurav Goswami on Tal

## Headline

ML Engineer @ Red Hat \| VLMs & LLMs \| Quantization \(GPTQ/AWQ\) \| vLLM \| PyTorch \| Edge AI

## About

• 8\+ years in ML — VLMs, LLMs, diffusion models, quantization, and edge deployment • Red Hat — VLM architectures, quantization research \(GPTQ, AWQ, SmoothQuant\), vLLM inference optimization, PyTorch & open\-source AI infra • Samsung Research — shipped camera AI on Galaxy S24/S23/Z Fold, 100M\+ devices, NPU/DSP optimization • Quantization: QAT, PTQ, INT4/INT8/FP16 mixed\-precision, structured pruning, knowledge distillation • Hardware: Exynos NPU, Qualcomm DSP, Jetson TX2, TensorRT, ONNX, <15ms on\-device latency • Vision: low\-light enhancement, diffusion\-based restoration, denoising, super\-resolution • Open\-source: YOLOX, YOLOE, quantization frameworks, vision architectures on GitHub • 1800\+ problems on Codeforces, CodeChef, LeetCode • https://gaurav14cs17\.github\.io/portfolio/

## Location

Bengaluru

## AI stack

claude

codex

cursor

deepseek

hugging face

kimi

## Work experience

Machine Learning Engineer at Red Hat, Sep 2025 \- Present · 1 yr 1 mo, Bengaluru, • Building and optimizing vision\-language model \(VLM\) architectures with efficient attention mechanisms for multimodal AI workloads • Driving quantization research \(GPTQ, AWQ, SmoothQuant, QAT\) to compress large transformer and diffusion models for low\-latency deployment • Contributing to the PyTorch ecosystem and open\-source AI tooling for scalable model development • Working with vLLM to optimize high\-throughput inference for large language and vision\-language models • Developing scalable training workflows using Training Hub for large\-scale model training pipelines

Lead Software Engineer \( Deep Learning & Computer Vision \) at Samsung R&D Institute India, Mar 2024 \- Sep 2025 · 1 yr 7 mos, Bengaluru, • Developed and deployed high\-resolution vision models for Galaxy S24, S23, and Z Fold series — shipped on 100M\+ consumer devices across 3 flagship generations • Led end\-to\-end AI pipeline for real\-time on\-device inference, optimizing vision transformer and CNN architectures for Samsung Exynos NPUs and Qualcomm DSPs • Drove quantization\-aware training \(QAT\) and post\-training quantization \(PTQ\) with per\-channel calibration and mixed\-precision \(INT8/FP16\) scheduling to reduce latency 3–5× without accuracy loss • Explored on\-device vision\-language model \(VLM\) architectures for adaptive scene understanding and intelligent camera control — prototyped lightweight CLIP\-style encoders fused with task\-specific heads • Built Bayer\-domain video denoising and NV21 low\-light enhancement modules, improving dynamic range and visibility in extreme illumination — integrated into camera HAL layer • Evaluated diffusion\-based restoration methods and designed latent\-space quantization strategies to make generative models viable for edge deployment

Senior Software Engineer \( Deep Learning & Computer Vision \) at Samsung R&D Institute India, Oct 2021 \- Mar 2024 · 2 yrs 6 mos, Bangalore Urban, • Developed low\-light image enhancement and denoising models with hardware\-aware optimization, deployed across mobile and embedded platforms with INT8 quantization for real\-time inference • Built AI\-based denoising, enhancement, and Bayer demosaicing pipelines optimized for NPU/DSP execution — profiled memory bandwidth and operator rooflines for bottleneck analysis • Implemented model compression via structured pruning, knowledge distillation, and weight sharing — delivering <15ms per\-frame latency on mobile SoCs • Built and optimized object detection and segmentation pipelines with quantization\-friendly architectures tailored for efficient on\-device inference • Developed reflection artifact removal and moire\-removal algorithms integrated into production camera pipeline for improved image quality • Contributed to Long Range Face Detection with efficient attention mechanisms, improving subject recognition at extended distances on Samsung flagship devices

Senior Deep Learning Engineer at SynergyLabs, Nov 2019 \- Oct 2021 · 2 yrs, • Vehicle Detection & Tracking — Designed custom feature\-pyramid detector optimized for multi\-class vehicle detection with bounding\-box post\-sorting and motion\-assisted temporal filtering for robust multi\-frame tracking; deployed on Jetson Nano with channel\-level pruning and ONNX export for real\-time edge inference • ALPR System — Developed anchor\-based detector for license plate localization with multi\-head OCR classifier and CTC\-based decoding; applied post\-training quantization \(INT8\) for deployment on Jetson TX2 at 30 FPS; integrated rule\-based logic for helmet detection, wrong\-way tracking, and triple\-rider analysis • Document OCR Pipeline — Designed lightweight CNN \+ RNN pipeline for structured text extraction from PAN, Aadhaar, and license images with alignment correction and ROI extraction; optimized with INT8 quantization and deployed on Jetson Nano for real\-time document verification

Open Source Contributor at Self Employed, Jul 2018 \- Aug 2025 · 7 yrs 2 mos, Remote, • Reparameterized Denoising Network — Built multi\-branch residual attention architecture with dynamic convolutional paths and channel re\-calibration on SIDD; designed reparameterization\-friendly blocks compatible with post\-training quantization \(PTQ\) for single\-pass inference fusion at deployment • PyTorch Quantization Framework — Engineered end\-to\-end QAT framework supporting per\-channel symmetric/asymmetric quantization, fake quantization ops, observer modules \(MinMax, Histogram\), and post\-training static quantization; benchmarked accuracy\-latency trade\-offs across INT8/INT4 precision levels • YOLOE Object Detection — Implemented YOLOE with enhanced E\-ELAN backbone, decoupled detection head, and anchor\-based target assignment; designed INT8\-quantization\-friendly architecture with COCO\-style evaluation and TensorRT export path • YOLOX PyTorch — Built anchor\-free detector with CSPDarkNet backbone, PA\-FPN, decoupled head, and SimOTA label assignment; optimized for real\-time edge inference with ONNX export, operator fusion, and mixed\-precision \(FP16/INT8\) deployment support • Low\-Level Vision Suite — Curated modular implementations of SRCNN, DnCNN, and DeblurGAN with perceptual loss and pixel shuffle upsampling; added quantization\-aware training paths and CLIP\-based perceptual quality metrics alongside PSNR/SSIM evaluation • TeethU2Net — Customized U2\-Net for dental image segmentation with multi\-scale side outputs, residual U\-blocks, and binary focal loss; evaluated FP16/INT8 ONNX export paths for clinical edge device deployment • Object Localization Network — Developed regression\-based localization CNN with smooth L1 loss, spatial dropout, and adaptive feature extraction; benchmarked on Pascal VOC with IoU\-based metrics and lightweight architecture design for mobile inference

Deep Learning Engineer at SynergyLabs, Jul 2018 \- Nov 2019 · 1 yr 5 mos, Gurugram, • Traffic Incident Detection — Implemented rule\-augmented pipeline to detect stopped vehicles, reverse motion, over\-speeding, and environmental factors \(fog, smog\); deployed as streaming video processor using GStreamer \+ TorchScript on industrial edge setups • Vehicle Axle Classification — Built custom HOG\-feature \+ CNN hybrid models for axle detection from undercarriage views with morphological filtering for axle isolation and class distinction • People Counting System — Developed background\-subtraction\-based counting system with bounding box merging and movement vector analysis; deployed in pure C\+\+ using OpenCV on Raspberry Pi and RockChip Pro — optimized for <50MB memory footprint • Synthetic Data with GANs — Trained Conditional GAN to generate number plate images with varied fonts, lighting, and occlusions; synthetic augmentation improved OCR accuracy by 12%\+ on rare and degraded captures

## Education

Bachelor of Engineering, Computer Engineering, Mahatma Jyotiba Phule Rohilkhand University \(MJPRU\), Bareilly

## Public links

- github: https://github\.com/Gaurav14cs17
- leetcode: https://leetcode\.com/gou\_rav
- codeforces: https://codeforces\.com/profile/scottaran9
- gaurav14cs17\.github\.io: https://gaurav14cs17\.github\.io/portfolio

[View the original profile](https://tal.club/meet/gourav-goswami)

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "Person",
      "@id": "https://tal.club/meet/gourav-goswami#person",
      "name": "Gaurav Goswami",
      "url": "https://tal.club/meet/gourav-goswami",
      "image": "https://tal.club/meet/gourav-goswami/profile-photo.jpg",
      "description": "Meet Gaurav Goswami, ML Engineer @ Red Hat | VLMs & LLMs | Quantization (GPTQ/AWQ) | vLLM | PyTorch | Edge AI based in Bengaluru. AI stack includes claude, codex, and cursor. Explore public work links including github, leetcode, and codeforces.",
      "jobTitle": "Machine Learning Engineer",
      "worksFor": {
        "@type": "Organization",
        "name": "Red Hat"
      },
      "hasOccupation": {
        "@type": "Occupation",
        "name": "Machine Learning Engineer"
      },
      "homeLocation": {
        "@type": "Place",
        "name": "Bengaluru"
      },
      "alumniOf": [
        {
          "@type": "EducationalOrganization",
          "name": "Mahatma Jyotiba Phule Rohilkhand University (MJPRU), Bareilly"
        }
      ],
      "knowsAbout": [
        "claude",
        "codex",
        "cursor",
        "deepseek",
        "hugging face",
        "kimi"
      ],
      "sameAs": [
        "https://github.com/Gaurav14cs17",
        "https://leetcode.com/gou_rav",
        "https://codeforces.com/profile/scottaran9",
        "https://gaurav14cs17.github.io/portfolio"
      ],
      "mainEntityOfPage": {
        "@id": "https://tal.club/meet/gourav-goswami#webpage"
      }
    },
    {
      "@type": "ProfilePage",
      "@id": "https://tal.club/meet/gourav-goswami#webpage",
      "url": "https://tal.club/meet/gourav-goswami",
      "name": "Gaurav Goswami on Tal",
      "description": "Meet Gaurav Goswami, ML Engineer @ Red Hat | VLMs & LLMs | Quantization (GPTQ/AWQ) | vLLM | PyTorch | Edge AI based in Bengaluru. AI stack includes claude, codex, and cursor. Explore public work links including github, leetcode, and codeforces.",
      "dateModified": "2026-09-05T15:36:03.693Z",
      "isPartOf": {
        "@id": "https://tal.club/#website"
      },
      "mainEntity": {
        "@id": "https://tal.club/meet/gourav-goswami#person"
      },
      "primaryImageOfPage": {
        "@type": "ImageObject",
        "url": "https://tal.club/meet/gourav-goswami/profile-photo.jpg",
        "contentUrl": "https://tal.club/meet/gourav-goswami/profile-photo.jpg",
        "caption": "Gaurav Goswami profile photo on Tal"
      },
      "inLanguage": "en-IN"
    }
  ]
}
```