Harsh Nagoriya

Amazon

Software Development Engineer

• Designed and launched a pre-development localization preview service integrated with Figma that reduced global launch timelines from 8 weeks to 1 week; enabled marketers to visually validate AI-powered localized content with in-situ mock reviews and automated the conversion of Figma mocks to Amazon marketing assets.
• Developed a microservice to manage the global expansion of Prime savings and benefits features, auditing and updating over 1500 marketing assets across 9+ Amazon marketplaces and compressing a 2-month manual process into a single day.
• Contributed to a new, event-driven microservice for replicating successful marketing experiments across 18+ Amazon marketplaces, improving the efficiency and scalability of global marketing campaigns.
• Led a cross-functional initiative with over 5 teams to launch the first-ever A/B test focused on customer retention, achieving statistical significance with a projected uplift of over 11,000 annualized Prime Members.
• Owned the end-to-end migration of an internal content management service from legacy hardware (NetScaler) to a modern AWS Application Load Balancer with zero downtime, eliminating critical security risks and enabling future cloud scalability.
• Designed and implemented a real-time, event-driven data pipeline using AWS Kinesis, migrating a critical service off a deprecated platform and ensuring 100% business continuity for experiment analysis dashboards.
• Developed the first comprehensive, end-to-end automated integration test suite for a critical marketing platform, providing 100% test coverage for the marketing experiment lifecycle and significantly reducing regression risks across two separate deployment pipelines.
• Drove key process improvements for the engineering team's sprint and operational excellence cadences, resulting in sustained 80%+ task completion rates and more efficient planning cycles.

Audere

Software Engineer

• Built serverless API components using AWS API Gateway and Lambda functions, supporting 10K+ daily requests with 99.9% uptime across production environments.
• Developed 5+ REST endpoints with Python Lambda functions, handling data processing and API integration for 3 mobile applications.
• Contributed to Infrastructure as Code using Terraform, automating deployment of AWS resources across dev/staging/prod environments.
• Built automated database migration pipeline using Alembic, reducing schema deployment errors by 95% and saving 15+ hours of manual database management per week.
• Integrated automated testing workflows into CircleCI pipelines, improving code quality and reducing manual testing overhead by 60% across development cycles.
• Developed comprehensive Android test automation using Espresso framework, increasing test coverage from 45% to 70% and catching 85% of bugs before production deployment.

Institute for Plasma Research

Project Intern

• Enhanced the development of Ethereum blockchain by utilizing Solidity, JavaScript, and Java and maintaining both client-side and server-side code. Complied with industry-standard software development procedures and crafted 5 UML diagrams to enhance comprehension and facilitate future maintenance.
• Participated in code reviews to ensure the quality and reliability of the final product.

Face Recognition on a PAAS

AWS Lambda, Amazon SQS, Amazon DynamoDB, Amazon API Gateway, Docker, RaspberryPI Mar 2022 – May 2022

• Designed and implemented a distributed application using AWS Lambda, Amazon SQS, Amazon DynamoDB, and Amazon API Gateway to perform real-time face recognition on real videos recorded by IoT devices, resulting in a highly scalable and efficient system.
• Utilized Docker to containerize the application and deploy it on an AWS Lambda, improving its portability and flexibility.
• Improved IoT operations latency by implementing optimized communication protocols and utilizing Amazon SQS for message queueing and asynchronous processing.
• Conducted rigorous testing and validation to ensure the accuracy and reliability of the face recognition system, achieving a high level of accuracy and reducing false positives.
• Tested the AWS Lambda function by sending over 500 requests in 5 minutes, identifying and resolving performance bottlenecks and improving the overall system responsiveness.

Face Recognition as a Service

Amazon Elastic Compute Cloud, Amazon SQS, Amazon Simple Storage Service, Flask Jan 2022 – Mar 2022

• Constructed a face recognition service based on Python, deployed on Amazon Web Services (AWS) EC2, incorporating the use of SQS and S3 for cost-efficient scaling.
• Implemented manually scripted load-balancers that automatically scaled in and out on demand to accommodate changing traffic patterns.
• Evaluated the scalability of the application by generating 1000 concurrent user requests, demonstrating its ability to handle high volumes of traffic efficiently.

Soccer Tournament Website

Java Server Pages, Servlets, J2EE, JQuery, AJAX, Bootstrap, MVC, MariaDB Sep 2021 – Dec 2021

• Developed a J2EE-based website with 6 distinct user roles, utilizing Agile software development principles, UML design concepts, Git version control, and Taiga scrum management.
• Revamped the user interface through integration of JQuery and AJAX scripts.
• Ensured high-quality results through compliance with specification-based and structural-based testing practices.

Complaint Management System

Java Server Pages, Servlets, J2EE, JQuery, AJAX, Bootstrap, MVC, MariaDB Feb 2021 – Apr 2021

• Developed a Complaint Management System using Java Server Pages and Servlets, reducing the paper-based system and alleviating the problems associated with the current method.
• Designed an electronic format for customer and user complaints registration, enabling them to register their complaints electronically, eliminating the need for a manual process.
• Created an intuitive user interface for the system, allowing customers and users to submit complaints easily and efficiently, leading to a 25% increase in customer satisfaction.
• Developed an electronic strategy for delivering announcements and general instructions to customers and users, improving communication and streamlining the process.
• Designed the frequently asked questions section for the system, providing customers and users with quick and accurate responses to their queries, reducing the workload of the customer service team by 30%.

FaceMask Detection System

Selenium, Data Collection and Processing, ResNet-101, Image Processing, RaspberryPI Sep 2020 – Dec 2020

• Developed a mask detection system using machine learning and deep learning techniques that achieved up to 96% accuracy in detecting whether a person has worn a mask or not.
• Trained a ResNet-151 convolutional neural network on a dataset of 18,236 images to classify the presence of masks in real-time video streams.
• Implemented the Adam optimizer to improve the training process and reduce overfitting, resulting in higher accuracy and reduced computational time.
• Conducted rigorous testing and validation to ensure the accuracy and reliability of the mask detection system, achieving a 96% success rate in detecting whether a person has worn a mask or not.
• Developed an automated alert system to notify authorities and individuals of non-compliance with mask-wearing regulations, improving public safety and reducing the spread of infectious diseases.

Student Attendance System using Face Recognition

Machine Learning, Eigen Faces, OpenCV, RaspberryPI, Python Feb 2020 – May 2020

• Designed and implemented a Raspberry Pi-based system to automate attendance tracking, reducing time, effort, and resources by 50%.
• Developed a face recognition system using Eigen matrix concept (Eigen Face) to detect and recognize human faces accurately and quickly through images and videos captured by a camera.
• Implemented the system to detect faces within the images and compare them with the database of registered faces to mark student attendance as absent.
• Designed and executed tests to ensure the accuracy and reliability of the face recognition system, achieving a 95% success rate in recognizing registered faces.

Helmet Detection System

Machine Learning, Single Shot MultiBox Detector, OpenCV, YOLOv3, Python Aug 2019 – Nov 2019

• Developed a machine learning model using Single Shot MultiBox Detector (SSD) to identify bikers among moving objects in real-time video streams.
• Designed a Convolutional Neural Network (CNN) to detect helmetless bikers and capture their number plates using YOLOv3 and Tesseract.
• Tested and optimized the model to improve accuracy and efficiency, achieving a 90% success rate in identifying helmetless bikers and capturing their number plates.
• Developed an automated data storage system that stores biker information and their number plates in a database for future reference and analysis.

Other Small Projects

• Handwritten Gujarati Characters Recognition

• Handwritten Digit Recognition

• Sentiment Analysis using Tweets

• ATM Database Management System

• Covid-19 Timeline Analysis

• 2D games using python & python library Pygame

• Walmart Sales Forecasting System

• Predication & Analysis of BigMart Sales

• Movie Recommendation System

• House Price Prediction System

• Wine Quality Prediction System

Live Facemask Detection System

International Journal of Imaging and Robotics™

2021 Volume 21, Issue I, Page No: 1-8, ISSN: 2231-525X

Attendance System using Face Recognition utilizing OpenCV Image Processing Library

International Journal for Research in Applied Science and Engineering Technology

2020 Volume 8, Issue VI, Page No: 1811-1814, ISSN: 2321-9653

DOI: 10.22214/ijraset.2020.6297

Live Helmet Detection System for Detecting Bikers without Helmet

International Journal of Knowledge Based Computer Systems

2019 Volume 7, Issue 2, Page No: 14-17, ISSN: 2321-5623

DOI: 10.5281/zenodo.4050483

Link: Journal's Article Page