Skip to content
View ketpatil77's full-sized avatar
🔥
ON FIRE
🔥
ON FIRE

Block or report ketpatil77

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ketpatil77/README.md

Ketan Patil

AI/ML Engineer, full-stack developer, and cybersecurity analyst focused on production systems, applied research, and measurable delivery.

What I Build

  • Production-grade AI/ML systems, full-stack web platforms, and security-oriented tooling.
  • Research-backed products that move from experimentation to deployable workflows.
  • Practical systems with quantified outcomes across product, networking, and cybersecurity work.

Featured Work

Professional portfolio system built with React, TypeScript, Vite, and motion-heavy UI patterns. Designed to present case studies, research, services, and engineering depth with production-ready frontend structure.

Interactive air-quality platform for India with city comparison, AQI storytelling, health context, forecast data, and live/fallback API handling. Built as polished public-facing product rather than plain dashboard.

Flask and PyTorch application for crop disease detection with offline-friendly workflow, Marathi-ready UX, generated reports, weather context, and farmer-oriented recommendations.

Experience

  • Meta: Jr. Network Analyst Intern
  • Sophos: Jr. Security Analyst Intern
  • DPIIT, Government of India: Tech Support Intern

Snapshot

  • 3 peer-reviewed publications
  • 14+ verified certifications
  • CCNP / CCNA certified
  • ~40% attack-surface reduction from authorized NMU penetration test

Research

  • Multi-Angle Industrial Inspection Fusion: viewpoint-invariant defect detection with 95.3% accuracy, AUC 0.991, and 31.4 FPS edge inference
    Paper: IJVRA2603948
  • Thermal + Depth Fusion for Predictive Maintenance: multimodal fault anticipation up to 72 hours before failure
    Paper: IJVRA2604277
  • FONTA: Failure Ontology for LLM Agents: ontology-driven analysis of autonomous agent failures across 1,200 trials

Core Stack

Python React TypeScript Flask Django PHP PyTorch Docker Redis TensorRT PostgreSQL Vite

Current Direction

Building systems where frontend quality, model usefulness, and operational reliability all matter at same time.

Pinned Loading

  1. ketpatil77.github.io ketpatil77.github.io Public

    Portfolio website

    TypeScript