Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    akshat_cv

    Uploaded by

    Akshat Gupta

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    akshat_cv

    Uploaded by

    Akshat Gupta
    11 views2 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    11 views2 pages

    akshat_cv

    Uploaded by

    Akshat Gupta

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 2

    ‭Akshat Gupta‬ ‭User ID‬‭-‬‭akshat.ag.2810@gmail.

    com‬

    ‭Tech Lead, Machine Learning @ InMobi‬ ‭LinkedIn‬‭-‬ ‭www.linkedin.com/in/agupta28‬

    ‭Kaggle Competitions Expert‬ ‭Kaggle‬‭-‬‭www.kaggle.com/akshatgupta2810‬

    ‭EDUCATION‬

    ‭Indian Institute of Technology, Kharagpur, India‬ ‭July 2015 - April 2019‬


    ‭Bachelor of Technology (Honours), Instrumentation Engineering CGPA - 8.73/10‬

    ‭Delhi Public School, Bhopal‬ ‭July 2014- April 2015‬


    ‭All India Senior School Certificate Examination, CBSE - 95.2%‬

    ‭FRAMEWORKS AND LANGUAGES‬

    ‭GCP Vertex AI, AWS SageMaker, GKE, Spark, Docker, AWS Lambda, Torchserve, TensorFlow, Keras, Pytorch‬

    ‭WORK EXPERIENCE‬

    ‭Tech Lead, Machine Learning, Glance InMobi, Bangalore‬ ‭July 2023 - Present‬
    ‭●‬ ‭Developed a new algorithm to generate short clips/trailers of long videos and deployed them at scale‬
    ‭using audio and video-based transcriptions. This resulted in an increase of 80% in time spent and a‬
    ‭Daily Run Rate of 5.6k USD/day‬
    ‭●‬ ‭Implemented personalized content recommendations for 200M+ users using a Real-Time Deep‬
    ‭Learning Recommendation System (DLRS), increasing engagement metrics by 47% (likes, downloads)‬
    ‭●‬ ‭Mentor a team of 10+ developers and lead university collaborations with Stanford and CMU on causal‬
    ‭inference research for recommendation systems‬

    ‭Senior Machine Learning Engineer, Glance InMobi, Bangalore‬ ‭July 2021 - July 2023‬
    ‭●‬ ‭Increased product image quality by 40% in the Natural Image Quality Evaluator (NIQE), reducing the‬
    ‭size by 5x. This led to a decrease in load time from 3-4 seconds to 0.5 seconds‬
    ‭●‬ ‭Implemented Multi Arm Bandit (Thomson sampling) for content recommendation for new users,‬
    ‭which led to a 40% increase in engagement‬
    ‭●‬ ‭Deployed custom-trained ML model for sending notifications to users for live streams based on their‬
    ‭affinity towards a particular live streamer, leading to a 30% increase in the conversion rate‬

    ‭Data Software Engineer, Société Générale, Bangalore‬ ‭June 2019 - July 2021‬
    ‭●‬ ‭Applied Image Processing to re-identify document signatures using angular features considering the‬
    ‭signature style, pixel connections and curves. Deployed at scale, saving ~200k euros per annum‬
    ‭●‬ ‭Designed APIs on Azure to fetch data from data lake to historize the financial deals and run ML models‬

    ‭Research Intern, VDEC Lab, University of Tokyo, Japan‬ ‭May - July 2017‬
    ‭●‬ ‭Implemented a custom CNN computation engine that took seven tiled input arrays from CPU branching‬
    ‭to 2 kernels, fetched seven input weights from FPGA DRAM, and calculated the weighted sum‬
    ‭●‬ ‭The engine was implemented on Xilinx Vertex -7 FPGA chip using MaxCompiler and Verilog‬
    ‭RESEARCH PROJECTS‬

    ‭Identification of Core and Penumbra in Acute Ischemic Stroke‬ ‭Oct 2020 - Sept 2021‬
    ‭Proposed a novel multi-path convolution leveraged attention-based deep network (MCA-DN) to address the‬
    ‭identification and localization of both direct and collateral blood flow restriction from MRI data [1]‬

    ‭Quantitative Analysis of Brain Herniation Using Deep Learning‬ ‭April 2020- Feb 2021‬

    ‭Implemented semantic segmentation using U-Net architecture to detect deformed midline shifts caused by‬
    ‭brain herniation [2]‬

    ‭PUBLICATIONS AND OUTREACH‬

    ‭[1] Anusha V.,‬‭Akshat Gupta‬‭, Nirmalya Ghosh "‬‭MCA-DN: Multi-path Convolution Leveraged Attention Deep‬
    ‭Network for Salvageable Tissue Detection‬‭" Journal of Computers in Biology and Medicine (Sept 2021)‬

    ‭[2] Manas Nag,‬‭Akshat Gupta‬‭, Hariharasudhan AS, A. Das, Nirmalya Ghosh "‬‭Quantitative Analysis of Brain‬
    ‭Herniation from Non-Contrast CT Images using Deep Learning‬‭" Journal of Neuroscience Methods (Feb 2021)‬

    ‭[3]‬‭Akshat Gupta‬‭, Anusha Vupputuri, Nirmalya Ghosh "‬‭Delineation of Ischemic Core and Penumbra Volumes‬
    ‭from MRI using MSNet Architecture‬‭” IEEE Engineering in Medicine and Biology Society, EMBC (July 2019)‬

    ‭[4] Mentor for‬‭Glance‬‭startup‬‭track for cancer detection in‬‭Gen AI Exchange Hackathon by Google‬‭(Oct 2024)‬

    ‭[5]‬‭Akshat Gupta‬‭"‭V
    ‬ ideo Highlights Creation‬‭" Speaker at Fifth Elephant Conference, Winter Track (Jan 2024)‬

    ‭[6]‬‭Akshat Gupta‬‭"‭H
    ‬ armonising Art and AI: Crafting Jazzy and Juicy Video Snippets‬‭" Speaker at Fifth Elephant‬
    ‭Conference, Monsoon Track (July 2023)‬

    ‭AWARDS AND ACHIEVEMENTS‬

    ‭Kaggle Competitions Expert‬ ‭Feb 2024‬


    ‭Earned three silver and three bronze medals in Kaggle competitions spanning tabular data, images, and‬
    ‭simulations, achieving the top 1.3% global ranking‬

    ‭Gandhian Young Technological Innovation (GYTI) Award, Govt. of India‬ ‭March 2023‬
    ‭Awarded for work in biomedical imaging for ischemic stroke segmentation, resulting in [1] and [3]‬

    ‭Data Science Hackathon, Shell.ai‬ ‭Dec 2022‬


    ‭Won third position in the general edition (1500 USD). The aim was to create AI-based solutions to make energy‬
    ‭more sustainable and affordable using solar power‬

    ‭Best Bachelor Thesis Award, IIT Kharagpur‬ ‭May 2019‬


    ‭Awarded for the thesis work in Biomedical Image Analysis along with a cash prize of Rs. 1000‬

    ‭National Talent Search Examination, Govt. of India‬ ‭March 2013‬


    ‭Selected as an NTSE scholar, securing top 99.7 percentile, with a monthly scholarship of Rs 2000 till graduation‬

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy