Summary
Overview
Work History
Education
Skills
Websites
Timeline
Generic

Harsh Trivedi

AHMEDABAD

Summary

To get success in an environment of growth and excellence and to earn a job that provides me job satisfaction along with self-development and helps me achieve organizational and personal goals.

Overview

4
4
years of professional experience

Work History

AI/ML Engineer

WebdataGuru
AHMEDABAD
03.2024 - Current
  • Developed a Image Matching API which gives a matching score of images.
  • Converting text data into vectors and finding similar products using vector search.
  • Creating s custom NER model which extract Attributes from a paragraph and then compare the values with each other.
  • Creating a Apache Airflow mechanism that connect all the pipelines of functionality and gives final output.

Data Scientist

Quarks Systems
Ahmedabad
03.2023 - 02.2024
  • I am developing an algorithm that detects similar images from the dataset and gives similar images as output
  • Developed a mechanism that extract stock price in real time and feed into the model.
  • Working on developing a process that dynamically automates the crawling process by creating and managing AWS EC2 instances
  • Developing a database infrastructure that handles large amounts of data without affecting the speed of the system.

Software Engineer

Meglyn Technologies Pvt. Ltd.
Ahmedabad
04.2020 - 02.2023
  • Developed automated data scraping pipelines, including scheduling and error handling, to ensure data consistency and quality
  • Conducted exploratory data analysis on scraped data to identify patterns, trends, and anomalies
  • Integrated scraped data with existing data systems and databases, such as MySQL, PostgreSQL, and MongoDB
  • Developed and implemented automated techniques to bypass CAPTCHAs and other anti-scraping measures, such as IP blocking, cookie tracking, and user agent detection
  • Utilized various third-party services, such as DeathByCaptcha, 2Captcha, and Anti-Captcha, to solve Captchas and other challenges
  • Successfully developing and maintaining over 200 web crawlers each quarter and utilizing a variety of scraping techniques, including Selenium, Beautiful-soup, and XPath
  • Developed algorithms that utilized various matching techniques, including title similarity, image similarity, attribute matching, and natural language processing, to find similar and exact matches of particular products
  • Designed and implemented a dynamic product-matching algorithm that could adapt to changes in user input data and modify its use cases accordingly
  • Implementing a custom framework plugin architecture that stores different functionality, which can be called dynamically as needed, demonstrating strong software development skills and a focus on efficiency and scalability
  • Developed a script that matched millions of products using title similarity and product SKUs, utilizing Pytesseract for OCR image reading
  • Utilized AWS RDS, AWS Lambda, and AWS S3 to take screenshots of websites and store images for future use
  • Designed and implemented a highly scalable database architecture that stores millions of data efficiently and handles them smoothly.

Education

B.Tech (Computer) -

Indus University Ahmedabad
Ahmedabad
05.2019

Master in AI/ML - Artificial Intelligence

IIIT Bangalore
Bangalore

Skills

  • Python 3
  • Selenium
  • Requests
  • Scrapy
  • PostgreSQL
  • MySQL
  • AWS S3
  • AWS Lambda
  • MongoDB
  • Pandas
  • Numpy
  • ML Regression & Classification Model
  • NLP
  • Git
  • Fast API
  • Apache Airflow
  • Apache MLflow
  • AWS Sagemaker
  • Spacy

Timeline

AI/ML Engineer

WebdataGuru
03.2024 - Current

Data Scientist

Quarks Systems
03.2023 - 02.2024

Software Engineer

Meglyn Technologies Pvt. Ltd.
04.2020 - 02.2023

B.Tech (Computer) -

Indus University Ahmedabad

Master in AI/ML - Artificial Intelligence

IIIT Bangalore

Similar Profiles

CREATE PROFILE
Harsh Trivedi