Good morning, I'm

Swastik Agrawal
Electrical & Electronics
Engineer.

Electrical & Electronics Engineering graduate with a CSIT minor. I build Python-based applications, integrate Generative AI, and work with SQLite for structured data handling. Currently exploring full-time opportunities where I can contribute and grow.

Get in touch ➜ View my work ➜

Projects

100%

Passion

∞

Learning

About Me

Who I am & what I do

An engineer who crossed disciplines — from circuits to code.

I'm Swastik Agrawal — a B.Tech Electrical & Electronics Engineering graduate with a minor in Computer Science & Information Technology from RGPV University. My engineering background wasn't a detour into tech — it was the foundation. It taught me to think in systems, debug under pressure, and design with purpose. Every circuit I analyzed, every signal I traced, shaped the way I approach software today.

I specialise in Python-based development and Generative AI. My primary stack is Python — FastAPI for clean and scalable solutions, with hands-on experience in LLM tooling and AI systems. I have worked with RAG for document querying, explored multi-LLM fallback approaches, and used SQLite for managing context in long-running AI conversations. I enjoy exploring how these technologies come together to build systems that are reliable, intelligent, and practical.

What separates my work from tutorial projects is the obsession with production readiness. I don't just build things that work on a happy path — I think about failure modes, latency, context limits, and cost from day one. Good backend engineering is invisible. You only notice it when it's missing.

Currently I'm deepening my expertise in agentic AI workflows — systems where models don't just respond, they reason, plan, and act autonomously toward a goal. I'm also building experience with AWS and Azure deployments, because the best AI system is useless if it can't scale or survive real traffic.

I'm open to full time opportunities where I can contribute to AI integration, or Python systems. If you're are looking for a candidate for this role — I'd love to be part of it.

Projects

Things I've built

Projects with a real purpose — each one solving something concrete.

01 / ChatRAG

ChatRAG — PDF Chatbot

A retrieval-augmented generation chatbot that answers questions strictly from a PDF's content. Chunks large documents intelligently, lets users swap PDFs at runtime, and runs smoothly on basic hardware — no expensive GPU needed. Scope is intentionally bounded to the document context, eliminating hallucinations entirely.

View on GitHub

02 / North

North — Context-Aware AI Chatbot

A reliable AI chatbot with automatic LLM failover — primary GPT-4 OSS 120B, auto-switches to Meta Llama 3.3 70B on downtime. Stores conversation history in SQLite and sends the last 250 messages as context on every prompt, making answers genuinely coherent over long sessions. Smart prompt limits prevent information overload.

View on GitHub

03 / PennyTrack

PennyTrack — Daily Expense Tracker

PennyTrack is a personal expense tracking desktop app built with Python. It lets you log and categorise your daily spending, then filter it by today, this week, this month, or all time. Expenses are stored locally using SQLite, keeping your data private and accessible offline. Each transaction supports a category, date, amount, and an optional note.

View on GitHub

04 / MailKey

MailKey — API Email OTP Authentication

MailKey is an email OTP authentication system built with Python. It sends one-time passwords via SMTP, optimised to land in the inbox. The sending domain was verified and configured through Cloudflare — setting up the necessary DNS records to establish trust with receiving mail servers. Clean, lightweight, and easy to integrate into any project.

View on GitHub

05 / Gravity

Gravity — Personal Desktop Assistant

Gravity is a voice-operated desktop assistant built with Python — one of my earliest projects. It uses speech recognition and text-to-speech to interact with the user, handling daily tasks through straightforward command logic. Simple by design, but meaningful in what it taught me about building things that actually respond to the real world.

View on GitHub

Skills