Shardul Ghuge

Software Engineer at aUToronto
  • Claim this Profile
Contact Information
Location
Mississauga, Ontario, Canada, CA
Languages
  • English Full professional proficiency
  • Hindi Native or bilingual proficiency
  • Marathi Native or bilingual proficiency
  • Kannada Native or bilingual proficiency
  • Urdu Native or bilingual proficiency
  • French Elementary proficiency

Topline Score

Bio

Generated by
Topline AI

0

/5.0
/ Based on 0 ratings
  • (0)
  • (0)
  • (0)
  • (0)
  • (0)

Filter reviews by:

No reviews to display There are currently no reviews available.

0

/5.0
/ Based on 0 ratings
  • (0)
  • (0)
  • (0)
  • (0)
  • (0)

Filter reviews by:

No reviews to display There are currently no reviews available.
You need to have a working account to view this content. Click here to join now

Credentials

  • Matlab Onramp
    MathWorks
    Nov, 2019
    - Sep, 2024
  • Project Management
    Flashpoint
    May, 2018
    - Sep, 2024
  • Standard First Aid, CPR and AED
    Action First Aid - Empowering People to Take Action!
    May, 2019
    - Sep, 2024

Experience

    • Canada
    • Automotive
    • 1 - 100 Employee
    • Software Engineer
      • Aug 2021 - Present

      • Developed a noise modelling technique for the car’s camera so that it can accurately map from noisy images to clean images via a Denoising Convolutional Neural Network (DnCNN) • Training the DnCNN requires vast amounts of data and thus custom built a Generative Adversarial Network (GAN) to create real-world noise models which greatly improved the performance of DnCNN • The team has built a SAE level 4 car which beats the current Tesla on-road models that are still level 2 and are thus the Consecutive winners of 2018, 2019, 2020, 2021 SAE and General Motors AutoDrive Challenge Show less

    • Bangladesh
    • Advertising Services
    • 1 - 100 Employee
    • Software Engineer Intern
      • May 2022 - Jul 2022

      • Developed an automated workflow to determine the contents of an Amazon truck when it reaches the fulfillment center via a custom-trained ML model. Used TDR images to train on AWS Rekognition and deployed on AWS Lambda • Based on the results of the ML classification, spot-check jobs are created for a particular yard associate with a latency of less than 40 ms. This mechanism serves as the feedback loop to consistently improve the performance of the ML model • The automated workflow is projected to improve the efficiency of the loading/unloading process by 10% and save 120+ hours of manual audit time across a single fulfillment center per month Show less

    • Canada
    • IT Services and IT Consulting
    • 1 - 100 Employee
    • Software Engineer
      • Mar 2021 - Sep 2021

      • Synthesized an ETL (Extract, Transform, Load) framework across several database platforms such as MySQL, PostgreSQL, Snowflake and BigQuery • Migrated the company’s financial records from Stripe to a Data Warehouse for the purposes of Analytical Querying to improve the revenue by 10% over 3 months. • Used Jamstack to decouple the frontend and backend operations of a website to allow for improved load times, easier scaling, lower operating costs and a streamlined developer experience • Synthesized an ETL (Extract, Transform, Load) framework across several database platforms such as MySQL, PostgreSQL, Snowflake and BigQuery • Migrated the company’s financial records from Stripe to a Data Warehouse for the purposes of Analytical Querying to improve the revenue by 10% over 3 months. • Used Jamstack to decouple the frontend and backend operations of a website to allow for improved load times, easier scaling, lower operating costs and a streamlined developer experience

    • Canada
    • Management Consulting
    • 100 - 200 Employee
    • Software Engineer Intern
      • May 2021 - Aug 2021

      • Working with the Intelligent Automation team to save the firm’s time, resources and money via Artificial Intelligence and Cognitive technologies • Developed an Intent Recognition Algorithm which performs NLP on the user input and aids the service-bots decipher typos which increased the task completion efficiency by over 25% • Built and deployed a chatbot using the Microsoft Azure framework which interacts with the employees to address their queries such as applying for a leave and reporting a company expense • The chatbot is used firmwide on a daily basis and saves 100+ employee hours weekly Show less

Education

  • University of Toronto
    Bachelor of Applied Science - BASc, Engineering Science
    2019 - 2023
  • Father Michael Goetz Secondary School
    High School Diploma, Specialist High School Major (SHSM) in Technology
    2015 - 2019

Community

You need to have a working account to view this content. Click here to join now