Skip to content
Aaryan Patwardhan

Applied AI Systems Engineer · Founder, QuantaSharp · Pune, India

I build AI systems that check their own work.

I'm Aaryan Patwardhan. The AI does the reading, fixed rules check the result, and anything uncertain goes to a person — tested, measured and shipped to real users.

How my systems work
  • AI model
  • Deterministic rule
  • A person reviews
  • Not working yet
  1. inputDocuments and data
  2. AI modelAI reads and proposes
  3. ruleRules verify the result
  4. personDoubts go to a person
  5. outputSaved, sent or acted on

Selected work

Each project with its real pipeline, its honest stage, and only numbers I've measured.

  1. Pilot-ready · v3.4Automation · Backend · Vision AI

    InvoiceAI

    Reads Indian GST invoices — digital PDFs, scans and phone photos — checks its own work, and marks anything doubtful for a person to review.

    • 83% field accuracy, 0 invented values (11 sample docs)
    • 136 automated tests
    • Accuracy gate in CI
    • Commercially licensed models only
    1. inputPDF, scan or photo
    2. AI modelLocal LLM reads it
    3. ruleRules check GSTIN, totals, tax
    4. personDoubts go to a person
    5. storageSaved · Excel export
    Case study: InvoiceAIPrivate code — demo on request
  2. LiveFull-Stack · Backend

    CramIQ

    Exam preparation for SPPU engineering students: a study planner, a study vault, progress streaks and a daily briefing email.

    • Live for students
    • Sandboxed service (systemd exposure 1.3)
    • Deploys roll back on failure
    • Nightly briefing emails
    1. inputNext.js app
    2. serviceFastAPI, sandboxed VM
    3. storagePostgreSQL + Redis
    4. AI modelGemini study material
    5. outputDaily briefing email
  3. Hackathon · team leadAutomation · Backend · Systems

    Hyron AI

    Finds the risky packages in a project's npm dependencies, explains each score, and plans safe upgrades. FUSION 2026 hackathon — team lead.

    • 24-hour hackathon build
    • OSV + EPSS + CISA KEV
    • Explainable 0–100 score
    • Team of four
    1. inputnpm lockfiles
    2. serviceDependency graph
    3. ruleOSV + EPSS + CISA KEV
    4. ruleExplainable risk score
    5. personUpgrade plan: auto / review / block
  4. PrototypeSystems · Backend · Full-Stack

    Aura — attendance from campus Wi-Fi

    Turns Wi-Fi accounting events into attendance records — no student app. A working prototype driven by a simulator.

    • Prototype
    • Redis Streams
    • PostgreSQL
    • Docker Compose
    1. inputWi-Fi events (simulator)
    2. serviceFastAPI ingestion
    3. storageRedis Streams
    4. AI modelAttendance rule + Isolation Forest
    5. outputPostgreSQL + dashboard
  5. Hackathon · AI core leadVision AI · Automation · Systems

    SentinelMesh

    AI-assisted drone response: YOLOv8 detection with two local LLM agents arguing before a dispatch. INSPIRON 5.0 (COEP) — AI core lead.

    • Hackathon build
    • YOLOv8
    • Two-agent debate
    • Simulated fleet
    1. inputRecorded video
    2. AI modelYOLOv8 detection
    3. ruleConfidence gate
    4. AI modelTwo LLM agents debate
    5. outputDispatch on a simulated fleet
    Case study: SentinelMeshPrivate code — demo on request
  6. Prototype · in progressSystems · Automation

    Ghost-Admin (prototype)

    A Linux daemon designed to notice runaway processes and step through safe, logged fixes. Work in progress — the AI step is not working yet.

    • Prototype
    • 7-stage design
    • JSONL audit log
    • Local LLM via Ollama
    1. inputRAM trend detection
    2. ruleWhitelist + baseline
    3. AI model · not working yetLocal LLM classifies
    4. outputGraduated remediation
    5. storageJSONL audit log

How I build

Four rules I hold every system to. You can check each one in the projects above.

  • Measure before claiming

    Accuracy comes from a labelled test set and a script anyone can re-run — never from a guess.

  • Let rules check the AI

    The model proposes; deterministic checks verify. GSTIN check digits, totals, confidence gates.

  • Show every doubt

    Anything uncertain goes to a person, in plain words. Nothing doubtful is marked complete.

  • Ship it like production

    Tests, CI, Docker, sandboxed services and rollbacks — on a cloud VM or a client's own machine.

Experience

  1. QuantaSharp, Pune

    Apr 2026 – Present

    Founder & Applied AI Systems Engineer

    • Built InvoiceAI, which reads Indian GST invoices (digital PDFs, scans and phone photos) with local LLMs via Ollama behind a FastAPI service with SQLite storage.
    • Designed a deterministic verification layer: GSTIN check-digit validation with OCR repair that is accepted only when the checksum passes, totals and CGST/SGST cross-checks, and seller/buyer correction from PDF text positions. Every doubtful field is flagged for review.
    • Wrote 136 automated tests and a labelled golden-set accuracy gate in GitHub Actions, so a model or prompt change that lowers accuracy cannot be merged; 83% field accuracy with 0 invented values on 11 sample documents.
    • Shipped it as an offline Docker package with Windows and Linux installers, and designed the dashboard for non-technical and older users.
  2. Code N Try, Pune

    Jan 2026 – Feb 2026

    Python AI/ML Development Intern

    • Built a house-price prediction model: explored the data with pandas and Seaborn, trained a scikit-learn regression on a train/test split, and saved it with joblib for a prediction script.
    • Built a Flask and SQLAlchemy web store with a product catalogue, session cart, checkout and an admin dashboard for adding and editing products.
    • Built a command-line chat assistant on the Google Gemini API, with the API key kept out of the code.

Education

B.E. Information Technology
SKN Sinhgad Institute of Technology & Science, Lonavala (Savitribai Phule Pune University)
Expected Jun 2028

Hackathons

  • FUSION 2026 — team lead, Hyron AI (participant)
  • INSPIRON 5.0, COEP — AI core lead, SentinelMesh (participant)
  • Smart India Hackathon 2026 (participant)
  • Decode SIH 2026 (participant)

Certifications

  • Front-End Development Internship — Cognifyz Technologies (2026)
  • 21 Projects, 21 Days: ML, Deep Learning & GenAI — GeeksforGeeks (2026)
  • Python Skill Up — GeeksforGeeks (2026)

Stack

What I've used in the projects on this page — and what I'm learning next.

AI and LLMs

  • Local LLMs via Ollama
  • Vision-language models for documents
  • Gemini API
  • LLM evaluation with golden sets
  • YOLOv8
  • scikit-learn

Backend and data

  • Python
  • FastAPI
  • PostgreSQL
  • Redis / Redis Streams
  • SQLite
  • SQLAlchemy

Infrastructure and delivery

  • Docker and Compose
  • GitHub Actions CI
  • Linux servers, systemd sandboxing
  • nginx
  • Vercel

Frontend

  • TypeScript
  • React
  • Next.js
  • Tailwind CSS

Learning now

From my six-month plan — being learned, not claimed.

  • Agentic AI: tool calling, MCP, LangGraph
  • AWS (Solutions Architect Associate)
  • Terraform
  • Kubernetes, GitOps, observability
  • Go
  • MLOps: MLflow, model serving

Let's build something that works.

Open to applied AI and backend internships, and to QuantaSharp projects. I reply within 24 hours.

patwardhanaaryan@gmail.com

LinkedInGitHubResume (PDF)QuantaSharp