Jan 2023 – Apr 2024 · 1 yr 3 mos · Bengaluru, Karnataka, India

• I contributed to an internal team, focusing on the development of management tools. My responsibilities included utilizing FastAPI, implementing PostgreSQL with SQL Alchemy, and integrating Azure BLOB for storage purposes. And also used Azure Repos for version control and documented those APIs using SwaggerUI and Postman.
• Implemented an ETL pipeline to extract metadata from 25+ data warehouses that were stored in Redshift, streamlining the process of loading data into PostgreSQL for the creation of a Data Dictionary. This significantly reduced the effort required for manual creation.
• Developed an ETL pipeline to extract metadata from Hive Metastore and data catalog platforms like Alation. Transferred the extracted data to PostgreSQL, contributing to the creation of training data for LLM models.
• Engaged in the development of an Airflow pipeline for status updates of the DAGs and notification of their status details to their designated Slack channel.

Feb 2022 – Jan 2023 · 11 mos

• Gathering the Technical requirements from the clients and evaluating the solutions with bottleneck, technical debt, future scalability, and designing the overall projects. Later conveying them to the Dev team and helping them with the pipeline for data processing, training the model, building the APIs, and deployment.
• Helping the interns and freshers with building up the Python solutions, Modules, and APIs and also with Database schemas and queries and also Built GUIs for the Annotation team to speed up and ease the jobs within "start-ups" deadlines and make teams productivity.

Dec 2020 – Feb 2022 · 1 yr 2 mos

• Built Person Re-identification PoC and the project identifying the person via different cameras and camera views. I've built a Siamese Network with a ResNet base model using Pytorch which compares a batch of images to identify the persons and save the records in PostgreSQL.
• Built an ANPR PoC for the Honda service center where Vehicle type and the Vehicle number plate are detected and recognized as all sorts of license plates (Single lined and double-lined). Here I've used Yolo V3 for vehicle type detection Yolo Tiny for license plate detection and CNN for OCR and finally dumped the data into MongoDB.
• Built Data Augmentation Pipeline for Indian double-lined two-wheeler license plate image dataset. Here, an empty number plate image will be taken with some tilt and the desired number PNG image is masked to create a fake license plate dataset using Python and OpenCV.
• Built Image Auto-Annotation for the desired label via AWS Recognition. This pipeline will take images and hit the AWS Rekgonition for coordinates of desired label class, where the JSON response is parsed into XML annotation format and saved using Python where later it will be converted to KITTI format to train the model.
• Built Motion Detection Pipeline where any movement in the video or stream is detected for certain frame intervals. The pipeline was first written in Python and later re-written in C++.
• Built Ubuntu Desktop Apps as part of Video Analytics app for drawing the Polygon ROIs and Line-Crossing on Images where desired ROI and line crossing's coordinates are recorded and fed into Analytics App using Python and Tkinter.
• Built Backend APIs using Python and Flask, interacting with SQL databases like PostgreSQL and Oracle SQL and NoSQL databases like MongoDB, dockerized and deployed in the EC2 Instance.
• Built PoC like Text Rekgonition using Python and Tesseract and built frontend using Bootstrap with Flask and deployed in AWS EC2 Instance within a day.

Jan 2020 – Jun 2020 · 5 mos · Hubballi, Karnataka, India

• I've built a CMS web app for the Smart Campus project where employees will register and later be assigned to specific buildings and floors for management with contact info.
• CMS system was built using Django with Bootstrap as frontend and MySQL as database managing all of these with XAMPP Server and sessions and password hashing were used while authentication.