I build AI systems, backends, and the infrastructure behind them.
From a city’s 311 chatbot to a college digital library, I build tools that make information easier to find and systems easier to run.
Available for a Spring 2027 co‑op, and full‑time from May 2027.
MS Computer Science · Northeastern
Boston, MA · Expected May 2027
City-service information, in plain language.
I built a chatbot for Fort Wayne’s 311 service that answered residents’ questions using retrieval-augmented generation, as a solo project I owned end to end. A query cache handled repeated questions, while the knowledge base grew around the information residents asked for most.
question → query cache
illustrative · a repeated question is answered from the cache
Corrected a validation error in LangChain's GPTCache integration when handling chat-generation results. PR #19427 was merged in March 2024.
From a design pattern to an illustrated tutorial.
Patternsmith turns software design patterns and code smells into tutorials with explanations, code, and diagrams. A staged pipeline develops and assembles each article, checks the output, and retries errors within set limits. If one topic fails, the rest of the batch can continue.
PipelineState ← topic
illustrative · every stage reads and writes one typed PipelineState
Course materials, in one searchable place.
I built Documan to bring scattered notes, lab manuals, and past papers into one library, available on the web and through Telegram.
Original platform
The Python/Flask system served 4,000+ students and delivered 200,000+ files before its retirement in May 2025.
Current rewrite
The Java/Angular rewrite adds four-tier access control and keeps search in sync with saved content. It is publicly available, with no users yet.
Design decisions
a write commits its row and outbox key together
Python / Flask · 4,000+ students · 200,000+ deliveries · 1,200+ active users · 99%+ uptime
Java / Angular · search being down never fails a write · public rewrite, no users yet
One configuration. Only the changes get deployed.
Hikari manages container deployments across machines from one configuration. It sends updates to an agent on each machine, which compares the new configuration with its last-applied state and updates only the affected stacks.
configuration updated
illustrative · an agent on each machine, over persistent connections
Extract document data with local AI.
OAAM processes documents on the user's machine through a browser interface. A local vision model reads an invoice and returns structured data. An optional MCP integration sends extracted results to Google Sheets.
How it works
drop a file
illustrative · output shape only · syncing to Sheets is a separate, optional step
Northeastern University, Khoury College of Computer SciencesSep 2026 – present
Nebulogic Technologies, HyderabadJun 2023 – Jul 2025
Nebulogic Technologies, HyderabadJun 2022 – Jun 2023
Geethanjali College of Engineering and Technology, HyderabadDec 2021 – May 2023
Choose a topic or enter a search to begin
Nothing matched. Try “backend”, “Redis” or “data visualization”.
↑ ↓ to move through results · esc to return to search
Browser-local keyword retrieval: each passage is a TF-IDF vector built when the site is compiled. Your query is analysed the same way, expanded with a short list of related terms, and ranked by cosine similarity over 43 passages. Results are grouped by project and ranked by their best passage. The map combines text similarity with category grouping; distances are illustrative.
Tools, systems, and collaborations
Academic projects
Select a technology to see where I’ve used it. Each number counts the projects and roles listed here.
AI & LLMs
Languages
Backend
Data
Infrastructure
Observability
Frontend
Testing
I got into software by fixing small, annoying problems. The fixes kept turning into systems.
Documan started that way. As an electronics engineering student, I wanted one place for my classmates’ notes, lab manuals and past papers, on the web and in Telegram. It ran for five years, served 4,000+ students, and never cost anything to host.
Nebulogic was my first job. As an intern I set up CI/CD across 40+ services. As a software engineer I built SMART AI Chat on my own, a 311 chatbot for the City of Fort Wayne, and cut the core CRM product’s startup from 20 seconds to 200 milliseconds.
Now I’m studying computer science at Northeastern and working as a teaching assistant for CS4530, Fundamentals of Software Engineering. Outside class I keep building: Hikari for container deployments across machines, Patternsmith for illustrated programming tutorials, and a NixOS configuration that keeps my environments reproducible.
The work I enjoy most makes other engineers faster: smoother deployments, clearer observability, and better day-to-day workflows.
I write up what I learn on the blog.
Northeastern University
MS, Computer Science
Sep 2025 – May 2027 (expected)
Geethanjali College of Engineering and Technology
Bachelor's, Electronics and Communication Engineering
Aug 2019 – May 2023