About Me
Since childhood, I've been fascinated by the inner workings of computers. I was that kid who dismantled desktops just to peer at the circuitry beneath, driven by curiosity and a desire to understand how these machines functioned. This early passion for technology steered me towards a career in computer science. I recently graduated from Georgia State University with a degree in Computer Science. Currently, I'm working as a Founding Engineer at a Stealth Startup, where I lead the architecture and development of enterprise AI SaaS platforms. My expertise primarily lies in technologies such as Python, TypeScript, React, Next.js, FastAPI, PostgreSQL, and AI/ML frameworks.
When I'm not coding, I indulge in my hobbies that include learning about space, cooking, and spending quality time with friends and family. I am constantly seeking to learn new skills and dive into diverse fields, enriching both my personal and professional life.
My projects
FinsightAI
Full-stack AI-powered expense tracker using OpenAI (spending insights), OAuth 2.0, and encrypted storage; organically adopted by 10+ friends tracking 200+ transactions and deployed on Vercel with GitHub Actions CI/CD and a dockerized stack.
Inventory Management for Chickfil A
Developed a stock inventory system using Flask and AWS. Integrated AI/ML models and used Power BI for reporting. Streamlined data analysis with Pandas and Excel.
TinyTasks - Voice-First AI Task Management App
Pivoted capstone project in 2 weeks after user feedback—integrated Groq Whisper for voice recognition and Llama models for intelligent task extraction, transforming a basic task app into a voice-first AI experience with automatic subtask generation. Shipped a cross-platform mobile app (iOS/Android) with a Flask AI backend, React Native/Expo frontend, and real-time Supabase calendar sync; dockerized services for deployment—reducing task entry from manual typing to 5-second voice commands with automatic structuring.
My skills
- Python
- PyTorch
- React
- TypeScript
- Docker
- Flask
- PostgreSQL
- AWS
- Git
- Supabase
- DigitalOcean
- Qdrant
My experience
Founding Engineer | Stealth Startup
San Francisco, CA (Remote)
Led the architecture and end-to-end development of an enterprise AI SaaS platform built around a custom conversational agent system and multi-tenant, production-grade infrastructure. Designed and deployed an AI agent framework using the OpenAI Agents SDK and ChatKit, implementing custom tool routing, streaming inference, and real-time document generation. Built a FastAPI-based backend with fully typed Python, modular service layers, async I/O, and optimized request pipelines; developed a Next.js 15/React 19 frontend with a collaborative editor, live markdown rendering, and state-synced UI. Architected the PostgreSQL schema with Row-Level Security for strict multi-tenant isolation; implemented JWT auth with refresh token rotation and Supabase integration. Developed a RAG pipeline using Qdrant (hybrid search + filtering) and Cohere embeddings, supporting user-scoped queries and namespace isolation. Implemented automated content-validation workflows combining Google Gemini and OpenAI structured outputs, including scoring heuristics, rule-based checks, and admin review flows. Built CI/CD pipelines (GitHub Actions) with typed linting (mypy), static analysis (Ruff, ESLint), formatting (Black), and test coverage across backend (pytest) and frontend (Vitest). Managed deployment on DigitalOcean using PM2 for process management and Nginx as reverse proxy; architected modular monorepo with 9+ feature-specific API modules and shared service layers. Stack: Python, FastAPI, TypeScript, Next.js, React, PostgreSQL, Supabase, Qdrant, OpenAI, Tailwind, Docker, Nginx
Feb 2025 - PresentFreelancer – Data Engineer | EMeRG Calgary, Canada
Calgary, Canada
Built an AI-powered pipeline to extract and structure medical equipment data from hospital websites using Crawl4AI, sitemaps, and LLMs (OpenAI, Anthropic). Validated output using Pydantic AI; stored structured data in PostgreSQL and Supabase for real-time analytics. Improved data accuracy by 35% and reduced extraction latency by 40% through optimized crawling and schema enforcement.
Nov 2024 – Jan 2025Student Assistant | Panther Dining
Atlanta, GA
Developed a stock inventory system using Flask, HTML, CSS, and AWS. Integrated AI/ML models for stock management and utilized Power BI for reporting. Streamlined data analysis using Pandas and Excel. Managed customer service and order processing.
Sep 2021 - Oct 2022Data Science Intern
Coimbatore, India
Developed a linear regression model in R to forecast product demand, increasing sales revenue by 15%. Created a Power BI dashboard to visualize sales data. Engineered an R-based ETL process for data integration, improving processing efficiency by 20%. Utilized clustering algorithms to identify customer segments.
May 2021 - Aug 2021Contact me
Please contact me directly at mukhil.baskaran27@gmail.com or through this form.