IbuildAIagents&automationsthatturncomplexproblemsintoworkingsolutions.

Not another AI experiment. Technology that solves real problems, from concept to deployment.

</>

Coding since 14. First Play Store app at 16, hand-coded before AI tools.

IIT MandiLeibniz University Hannover15 hackathons won
50+
websites administered
IIT Mandi's student server, 3,000+ users
15
hackathons won
incl. events by IIT Bombay, Guwahati, Madras
AIR 9
among 15,000+
Shaastra Juniors, IIT Madras
Why work with me

Not just writing code. Building solutions.

I believe good engineering starts with understanding the problem, not choosing a technology.

  1. 01

    Understand the problem

    I look beyond the initial requirement to the underlying challenge, the people using the solution and the outcome that matters.

  2. 02

    Engineer the solution

    I bring together AI, software development, APIs, data pipelines and automation to design solutions that are practical and scalable.

  3. 03

    Build, deploy and improve

    I own implementation, integration, testing and deployment, so it works beyond a demo.

The objective isn't to use AI everywhere. It's to use technology where it creates measurable value.

How I'd take a rough idea
The brief
“We want an AI chatbot.”
  1. Who it's really for
    A support team answering the same 40 questions every day
  2. What actually hurts
    Customers wait hours for answers that take seconds
  3. The first version
    An assistant that answers from your help docs and hands the hard cases to a person
  4. How we'd pitch it
    “Answers in 10 seconds, day or night”, not “we use AI”

Examples of how I think through a brief, not client case studies.

Services

What I can build for you.

Four kinds of solutions, often combined in one project: the AI, the automation around it, the product people use and the infrastructure that keeps it running.

Agentic AI & intelligent assistants

AI systems that go beyond answering questions.

  • Autonomous AI agents and multi-agent workflows
  • Document intelligence and knowledge assistants
  • Retrieval-Augmented Generation (RAG)
  • LLM tool calling and intelligent information retrieval
  • Research and decision-support systems
ExampleAn AI research assistant that retrieves information, verifies claims and provides evidence-backed answers.

Business process automation

Reduce repetitive work and create intelligent workflows.

  • AI-powered workflow automation
  • API integrations and backend automation
  • Intelligent document and data extraction
  • Automated reporting and information processing
  • Real-time data processing and decision systems
ExampleAutomating a multi-step business workflow that currently needs repetitive manual work.

AI-powered applications & products

Turn ideas into working digital products.

  • AI-powered web applications
  • Custom dashboards and internal tools
  • Backend and API development
  • Mobile applications
  • AI integrations into existing products
ExampleA complete application with AI capabilities, backend architecture and production deployment.

AI infrastructure, deployment & engineering

Build systems that can operate reliably.

  • Python backend development
  • Docker-based deployments
  • Cloud infrastructure and hosting
  • Linux administration and server security
  • API integrations and production support
ExampleDeploying and maintaining applications with the right infrastructure and security practices.
Swipe for more →
My toolkit
01 / 05 · AI & agents

A brain for your business.

Assistants that read, reason and answer from your own documents, and agents that search, decide and act on their own.

  • OpenAI
  • Claude
  • Google Gemini
  • Hugging Face
  • LangChain
  • PyTorch
Projects

Selected engineering work.

Case studies, not thumbnails: the challenge, what I engineered, how it was validated and what it shows. Academic, competition and production work are labelled as such.

step 1
Your question
step 2
Finds papers
step 3
Checks each claim
step 4
Answer + sources
[1][2][3]
every claim is checked against a real paper before you see it
Agentic AI · Research · 2026100% citation accuracy

SciAgent

An agentic AI research assistant that verifies what it says.

The challenge
AI assistants can produce convincing answers without checking whether the underlying information supports their claims. In research, that is a critical limitation.
What I engineered

An agentic research assistant that searches academic papers, retrieves relevant evidence, evaluates claims and gives grounded responses.

  • Five specialised LLM tools
  • BGE embeddings and FAISS retrieval
  • Cross-encoder reranking
  • Natural Language Inference (NLI) for claim verification
  • A framework-free LLM tool-calling loop
Validation
100% citation accuracy on a hand-annotated benchmark100% abstention accuracy0.92 held-out fact coverage
What it shows
Engineering AI that goes beyond generating text: retrieval, reasoning, verification and reliability.
Python · Agentic AI · FAISS · BGE · Cross-encoders · NLIExplore on GitHub ↗
live
customers regroup live as their spending changes
Streaming ML · Inter IIT Tech Meet 14.0 · 2025Inter IIT 14.0

Customer Targeting

Real-time customer intelligence through streaming data and machine learning.

The challenge
Traditional customer segmentation goes stale as behaviour changes. Businesses need to understand customers as transactions happen.
What I engineered

A distributed streaming pipeline that processes transaction events and maintains a live Customer 360 state.

  • Stateful joins and reducers
  • Incremental feature updates
  • Distributed streaming architecture
  • Online machine-learning inference
  • Concept-drift handling
Validation
≈0.83 streaming accuracy
What it shows
Distributed systems, streaming data, machine learning and real-time decision intelligence.
Pathway · Python · Streaming systems · Online MLExplore on GitHub ↗
✂ 12:40 · laughter peak✂ 47:05 · big reveal
the loudest, most emotional moments are marked for clipping
Applied ML · Speech · 2025

PodClip

Turning long-form podcasts into short-form content intelligence.

The challenge
Finding the engaging moments in long podcast recordings takes hours of manual listening and editing.
What I engineered

A backend pipeline that ingests YouTube podcasts, extracts audio, transcribes and separates speakers, and identifies high-engagement moments.

  • Audio extraction and processing
  • Whisper-based transcription
  • Speaker diarization
  • Sentiment analysis
  • Vector indexing and content intelligence
What it shows
Combining applied ML, speech processing and backend engineering into a useful content workflow.
Python · Whisper · Hugging Face · Applied MLExplore on GitHub ↗
Joined the group 🙏
Welcome! Story at 8?
Count me in
Sharing the link now
Shipped to Google Play
Shipped to App Store
chat, profiles and followers, released to both app stores
Mobile · Production · Dec 2025 – Feb 2026Google Play & App Store

MyItihas

Production mobile app development, from engineering to app-store release.

The challenge
A social mobile app needs more than screens: authentication, data models, APIs, user interactions and reliable deployment.
What I engineered

Owned the full product development lifecycle and independently shipped production builds to Google Play and the Apple App Store.

  • Peer-to-peer and group chat
  • Authentication and profile management
  • Follower / following system
  • Backend data modelling
  • API integration for search and chat storage
What it shows
End-to-end product ownership, mobile engineering, backend integration and production execution.
Flutter · Supabase
›a bakery site with a menu and online orders
one sentence in → a working website out
AI agents · Hackathon · 20251st place · KrackHack 2.0

Webspark

An AI-powered website builder.

The challenge
Getting a website made is slow and expensive for a small business.
What I engineered

A system that turns a plain-language instruction into a working website through AI-assisted design, development and deployment.

  • Natural-language brief to site plan
  • AI agents for design and code
  • Automated deployment
What it shows
Orchestrating multiple AI agents into one product flow, built and demoed under hackathon pressure.
Python · AI agents · Next.js
The story behind the builder

Curious by nature. Driven to create.

Technology was never just a subject to study. It was something I wanted to understand, experiment with and build.

I wasn't learning because it was part of a curriculum. I was learning because I wanted to turn ideas into something real.

  1. Class 4

    Rubik's cubes

    A simple cube turned into a fascination with harder and harder puzzles, and the satisfaction of solving them.

  2. Age 14

    Curiosity turns to code

    Started learning Python, web development and mobile app development, not for a curriculum but to make ideas real.

  3. Age 16

    First app on the Play Store

    A full year building and publishing an Android app alone, every line by hand, before AI coding tools existed.

  4. Class 10

    Keynote at GDG, UPES Dehradun

    Delivered a hands-on Flutter session as a keynote speaker at a Google Developer Group event.

  5. Lockdown

    Competitions & hackathons

    Started competing online, including events run by IIT Bombay, IIT Guwahati and IIT Madras.

  6. Lockdown

    2,000+ learners on YouTube

    Started a channel teaching Python and Flutter that grew organically past 2,000 subscribers.

  7. IIT Mandi

    From curiosity to engineering

    Cybersecurity, AI, machine learning and systems. Google Cybersecurity certificate, Cybersecurity Club, server administration, mentoring and teaching.

  8. Today

    Agentic systems & automation

    Software engineering, applied AI, agentic systems and automation, with the same motivation: understand deeply, build something useful.

Curiosity isn't just about asking questions. It's having the courage to explore the answers, and the ability to build something from what you discover.
Credentials & recognition

Education, wins and responsibility.

Education2024 – 2028
Indian Institute of Technology, Mandi
B.Tech, General Engineering, specialisation in AI & Robotics
EducationOct 2026 – Mar 2027
Leibniz University Hannover, Germany
Exchange semester, Computer Science & AI

Wins & recognition

  • ★
    1st place, KrackHack 3.0
    GDG IIT Mandi · 2026
  • ★
    1st place, KrackHack 2.0
    GDG IIT Mandi · 2025
  • ★
    1st place, Space Code 2026
    IIT Mandi · 2026
  • ★
    AIR 9 among 15,000+
    Shaastra Juniors, IIT Madras
  • ★
    1st place, Case Study Competition
    Shaastra Juniors, IIT Madras
  • ★
    Google Cybersecurity Professional Certificate
    Google

15hackathons won, including events run by IIT Bombay, IIT Guwahati and IIT Madras.

Leadership & responsibility

  • System Administrator
    SAIC, IIT Mandi

    Administer 50+ websites on the primary student server for 3,000+ students and faculty: Docker deployments, DNS and server security.

  • Tutor
    PRAYAS 3.0

    Mentored 100+ students in hands-on Arduino and machine learning.

  • Core Team
    Kamand Prompt, Programming Club

    Delivered a web development session to 500+ students.

How I work

From an idea to a working solution.

  1. 1

    Understand

    We discuss the business problem, the intended users and what success should look like.

  2. 2

    Architect

    I pick the right technology, design the solution and define a practical development plan.

  3. 3

    Build

    I develop in focused iterations, validate functionality and share progress.

  4. 4

    Deploy

    I integrate, test and deploy the solution into its intended environment.

  5. 5

    Improve

    I help refine the product based on feedback, performance and actual usage.

Clear communication, practical engineering and a focus on delivery.

Let's work together

Have a problem worth solving?

Maybe you want to automate a repetitive workflow, build an AI assistant, create a new AI-powered product or bring intelligence into an existing application. Let's explore the problem and figure out what we can build.

Email me
Hannover, Germany · available for remote collaboration internationally
What do you want to build?

Opens your email app with the message ready to send.