Milan Barot

The Interview Assistant (originally developed as Job Bandit) is a premium, desktop-oriented productivity application designed to provide real-time AI support for job seekers during technical interviews and preparation. Built with a "stealth-first" philosophy, the app presents itself as a "Windows Runtime Host" in the Task Manager and features a modern, high-performance interface with glassmorphism aesthetics and smooth transitions. It serves as a sophisticated bridge between the user and advanced Large Language Models, leveraging specialized configurations for GPT-4 and GPT-5 (nano, mini) and next-generation reasoning models to deliver tailored, context-aware assistance based on the user's uploaded resume and specific job descriptions.

Functionally, the application automates the interview workflow by offering robust session management, detailed performance tracking (including Time-to-First-Token metrics), and high-accuracy screenshot analysis for visual queries. Users can initiate timed sessions that securely ground AI responses in their professional profile, while features like "Mini Mode" (activated via Ctrl+Q) and window transparency allow for an inconspicuous, low-profile presence during high-stakes evaluations. The system also includes a secure, hardware-locked licensing mechanism, searchable historical session logs with syntax-highlighted code blocks, and the ability to export entire conversation transcripts to elegantly formatted markdown files for later review.

The “Monthly Music Sync” project is designed with the goal of synchronizing a user's liked songs between YouTube Music and Spotify platforms using Python and relevant APIs. The ELT pipeline is built using Python, AWS S3, YouTube Data API, Spotify API, and integrates with third-party libraries such as spotipy and youtube_dl. The project retrieves music data from YouTube Music and Spotify using their respective APIs and processes this data by extracting metadata and searching for corresponding tracks on Spotify. The processed data, specifically YouTube video IDs, are stored in an AWS S3 bucket for tracking synchronized songs.
The pipeline is automated to run monthly via Apache Airflow, ensuring periodic synchronization of liked songs.
Future enhancements include further integration with Apache Airflow for automation, development of a React App for a user-friendly interface, and enhanced error handling mechanisms.

python/libraries: spotipy, youtube_dl, Pandas, plotly.
tech/tools: Python, AWS S3, YouTube Data API, Spotify API, Apache Airflow, React (for future enhancements)

With the aim of retrieving the user's music data via Python's REST API and staging it to the Postgres server, the ELT pipeline has been designed using a combination of Python, Postgres database, Dagster for automation, docker for containerization, and Power BI for visualization. The data is transformed in a number of ways using pandas to produce useful insights that can be used to build PowerBI dashboards and visualizations. With Dagster, the pipeline is automated to run every month. The project's ultimate objective is to discover the user's monthly music preferences by analyzing particular characteristics, such as the recently released "audio-features" by Spotify.

python/libraries: Pandas, plotly, urllib, pandasql, request.
tech/tools: Dagster, Docker containers, Power BI

Developed using web development essentials such as HTML, PostCSS and JavaScript (Babel & Webpack) and Node.js.
The website was developed as per the "mobile-first" design approach such that the devices downloads only the data that is appropriate for the current device, thereby providing faster loading/reloading time.

An interactive “University” website clone developed using using PHP, JavaScript, WordPress theming & the WordPress REST API.

Created “like” feature, “Live/on the fly” search functionality, WordPress custom field Post types using JavaScript and JQuery which was then connected to the backend using JSON and WordPress Rest APIs and created raw JSON data.
libraries: Gulp, JQuery, Bootstrap, WordPress RestAPI, Font Awesome
tech/tools: HTML, SASS, JavaScript, PHP, WordPress, Git

I am a Data Engineer with 6 years of experience specializing in the architecture and maintenance of high-stakes data pipelines within the healthcare, real estate, and telecom sectors. My expertise lies in bridging the gap between legacy infrastructure—like the complex EDI and CMS workflows I managed at Blue Cross Blue Shield—and modern cloud-native solutions using Azure Databricks and LLM orchestration.

I am a hands-on builder who values operational stability as much as innovation. I’ve led offshore teams through high-pressure recovery efforts and managed over 30 production deployments in environments where data accuracy is a regulatory requirement. I approach engineering with a product-focused mindset, recently developing custom AI-driven applications that utilize low-latency streaming and RSA security to solve real-world efficiency gaps.

Here is my downloadable resume.