Skip to content
View ANSHAM1's full-sized avatar
🏠
AT University
🏠
AT University
153 followers · 264 following

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Shark

Highlights

Block or report ANSHAM1

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
ANSHAM1/README.md

ANSHAM MAURYA

AI Systems Engineer • Agentic AI • Backend & Distributed Systems • Deep Learning

Building AI Systems, exploring distributed architectures, and turning ambitious ideas into production-ready software.

  • ⚙️ I build daily with: .py • .cpp • .sql • .fastapi • .docker • .langgraph
  • 🧠 I'm mostly active within AI Systems, Backend Engineering, and Agentic AI
  • 🚀 Building: MODELISE, TorchLessCUDA, InsertionAI, SentinelAI
  • 💬 ping me about AI, LLMs, System Design, Backend Engineering, Distributed Systems, and Software Architecture
  • 🌐 Portfolio → ansham1-portfolio.vercel.app

Languages
Python • C++ • Rust • Java • JavaScript

AI / Machine Learning
PyTorch • Keras • NumPy • Pandas • CUDA

LLM / Agentic AI
LangChain • LangGraph • RAG • AI Agents • Tool Calling • Prompt Engineering • Vector Databases

Backend Development
FastAPI • gRPC • REST APIs • Node.js • Express.js • Microservices • Async Programming

Databases
Microsoft SQL Server • PostgreSQL • MySQL • MongoDB • SQLite

DevOps / Infrastructure
Git • GitHub Actions • Docker • Docker Compose • Kubernetes • Linux

◈ MODELISE

A production-ready AI model deployment and governance platform designed for secure, scalable, and modular AI infrastructure. It supports custom ML/DL model deployment, LLM orchestration, retrieval-augmented generation, autonomous agent workflows, and distributed backend services through a unified API layer.

Highlights: Custom ML/DL Models • LLMs • LangGraph • LangChain • RAG • Distributed Systems • FastAPI • gRPC • Python • SQL Server • Docker

◈ TorchLessCUDA

A high-performance deep learning framework built entirely from scratch, implementing a complete Convolutional Neural Network library without external ML frameworks. Includes custom CUDA kernels for forward and backward propagation, GPU memory management, and optimized matrix operations.

Highlights: C++ • CUDA • CMake • CNN Library • GPU Programming • Neural Networks • Linear Algebra • Performance Optimization

◈ SentinelAI

An intelligent Network Intrusion Detection System that performs real-time traffic analysis and anomaly detection using a high-performance systems architecture.

Highlights: Rust • Tauri • Network Security • Packet Analysis • Concurrency • System Programming

“Code is the closest thing we have to magic ✨”

Pinned Loading

  1. TOrchLessCUDA TOrchLessCUDA Public

    TorchLessCUDA is a deep learning framework built entirely from scratch using Modern C++20 and CUDA, implementing tensor operations, GPU training, and inference without relying on existing machine l…

    C++ 2

  2. AI_Research_Assistant_Agent AI_Research_Assistant_Agent Public

    Autonomous AI research assistant that can analyze documents, search knowledge bases, perform calculations, and generate structured research reports.

    Python 1

  3. SentinelAI_Nids SentinelAI_Nids Public

    An AI-driven network intrusion detection system built from scratch, combining machine learning and deep learning techniques to analyze network behavior, identify anomalies, and detect potential cyb…

    Rust 1

  4. FlowForge-Mini_LCEL_Pipeline_Engine FlowForge-Mini_LCEL_Pipeline_Engine Public

    A lightweight implementation of a LangChain Expression Language (LCEL)-inspired pipeline execution framework built from scratch in Python using Object-Oriented Programming, operator overloading, an…

    Python 1

  5. Embedded_LSM_KV_Database Embedded_LSM_KV_Database Public

    A lightweight embedded key–value database built from scratch using modern C++, implementing an LSM-Tree storage engine with write-ahead logging, SSTable persistence, and efficient read/write operat…

    C++ 1

  6. Tic-Tac-Toe-AI Tic-Tac-Toe-AI Public

    A Tic-Tac-Toe AI built in modern C++ using the Minimax algorithm with memoization (dynamic programming), efficient last-move win detection, and scalable board-size support.

    C++ 1