Skip to content
View ChinmayHudedamani's full-sized avatar
3 followers · 4 following
  • Banglore
  • 21:53 (UTC +05:30)

Block or report ChinmayHudedamani

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.

Content in all repositories owned by your account will be closed.
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
ChinmayHudedamani/README.md

Hi there, I'm Chinmay V Hudedamani 👋

Typing SVG

Email GitHub Location Status

🏛️ Executive Summary & Engineering Focus

I am an AI Systems & High-Performance Software Engineer based in Bengaluru, India. My engineering philosophy revolves around breaking through the Memory Bandwidth Wall and latency ceilings by designing hardware-software co-designed architectures, native C++20 acceleration pipelines, and memory-constrained inference runtimes.

  • 🎓 Undergraduate Scholar in Computer Science & Engineering at Nitte Meenakshi Institute of Technology (NMIT), Bengaluru.
  • ⚡ Low-Level Inference & Edge AI: Designing fused W4A16 GEMM quantization kernels, dynamic PagedAttention subsystems, and sub-100ms TTFT runtimes on consumer NVIDIA hardware.
  • 🛰️ Autonomous Geospatial & Radar Intelligence: Author of AEGIS-SEAS — an ultra-fast C++20 sovereign maritime surveillance platform processing Copernicus Sentinel-1 C-Band SAR imagery in under 1.1 seconds.
  • 🔒 Formal Verification & Systems Security: Architecting systems that replace brittle CRUD patterns with formally verified DFA state machines and tamper-evident Merkle structures.

🌟 Featured Flagship Repositories

🛰️ AEGIS-SEAS

Autonomous Satellite Radar Oil Slick Intelligence & Sovereign Polluter Attribution Platform built in modern C++20 for the Indian EEZ. Features native radiometric calibration, 2D CA-CFAR metallic target extraction, embedded 2-channel U-Net inference on real Sentinel-1 weights, and reverse Lagrangian drift dispersion hindcasting.

👉 View Repository | Launch Mission Control

⚡ Edge-LLM-Runtime

High-throughput, air-gapped local inference engine designed for consumer NVIDIA GPUs. Features group-wise INT4 weight quantization (G=64), uint32 bit-packing, register-level fused dequantization GEMM kernels, 2048-token sliding-window PagedAttention with attention sinks, and live performance telemetry.

👉 View Repository

🚀 AUGMENTiX AI Systems Starter

Production-grade boilerplate starter repository and 8-week incubation cohort syllabus designed to onboard engineering teams for high-tier national hackathons. Includes formal VRAM memory budget calculators, hardware GPU profilers, Pydantic v2 schemas, and strict Git contribution standards.

👉 View Repository

⚽ Premier League Predictor

Advanced predictive analytics system modeling match outcomes, title races, player synergy, transfer valuations, and club owner strategies across 10,800+ historical EPL matches using calibrated ensemble estimators and interactive visual dashboards.

👉 View Repository

🛡️ Verified DFA HRMS Platform

A next-generation enterprise platform replacing error-prone CRUD with formally verified Deterministic Finite Automata (DFA) state machines, cryptographically tamper-evident Merkle audit trees, and zero-knowledge encrypted payroll data structures.

👉 View Repository

🎓 Student Placement Predictor

End-to-End Big Data analytics pipeline predicting student employment probabilities using 5-Fold Stratified Cross-Validation, feature importance attribution, and an interactive Flask deployment dashboard.

👉 View Repository

🛠️ Core Tech Stack & Systems Toolkit

Domain Technologies & Tools
Low-Level & Systems C++ CUDA OpenMP CMake Linux
AI, Inference & Quantization PyTorch Transformers INT4 Quant Scikit-Learn XGBoost
Data & Scientific Computing NumPy Pandas Polars Plotly
APIs, Web & Tooling FastAPI Flask Typst Leaflet Git

📊 GitHub Activity & Telemetry

GitHub Stats Top Languages

GitHub Streak

Engineered with precision by Chinmay V Hudedamani • Bengaluru, India

Popular repositories Loading

  1. Placement-Prediction Placement-Prediction Public

    End-to-End Big Data Analytics & ML Pipeline for Student Placement Prediction (XGBoost, 5-Fold Stratified CV, 89.16% Accuracy, Interactive Flask Web App)

    Python

  2. edge-llm-runtime edge-llm-runtime Public

    Chinmay's AI Assistant (edge-llm-runtime) is a 100% offline, high-efficiency local inference engine for NVIDIA consumer GPUs featuring group-wise INT4 weight quantization (3.39x memory reduction), …

    HTML

  3. human-resource-management-system human-resource-management-system Public

    A next-generation HRMS platform replacing legacy CRUD with formally verified DFA workflows, tamper-proof Merkle logs, and zero-knowledge payroll encryption.

    TypeScript

  4. premier-league-predictor premier-league-predictor Public

    Advanced Machine Learning system predicting English Premier League title winners, match outcomes, player synergy, emerging talents, transfer valuations, and club owner strategies across 10,800+ his…

    Python

  5. aegis-seas aegis-seas Public

    Autonomous Satellite Radar Oil Slick Intelligence & Sovereign Polluter Attribution Platform (Modern C++20 | Copernicus Sentinel-1 C-Band SAR)

    C++

  6. augmentix-ai-systems-starter augmentix-ai-systems-starter Public

    Production-grade development template, engineering standards, and modular infrastructure for building edge AI, INT4 runtime inference engines, and resilient multi-agent systems.

    Python