Skip to content
View HiteshSingh21's full-sized avatar

Highlights

  • Pro

Block or report HiteshSingh21

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
HiteshSingh21/README.md

Hitesh Singh

AI Engineer • Agentic Systems • Realtime GenAI • DevOps

FastAPI | Agno | PyTorch | FFmpeg

Typing SVG


🏛️ Engineering Philosophy

"Building intelligent systems that scale, not just scripts that run."

CS Student @ KIIT (9.59 CGPA) | 5+ Years Java | Specializing in Agentic AI, RAG, and MCP. I design deterministic, multi-agent systems tailored for open science and complex data-driven research.

  • Current Focus: Agentic Orchestration, Distributed AI Systems, and Model Context Protocol (MCP).
  • Goal: Contributing to high-impact Open Source projects for GSoC '26 with a focus on Genomics Standards (GA4GH), Scientific Data Infrastructure (EMBL-EBI), and Developer Productivity (Jenkins).
  • Core Competency: Python Performance Optimization, Enterprise Java Architecture, and Deterministic RAG Pipelines.

🛠️ Technical Infrastructure

AI & Agentic Systems


Backend & Enterprise


Languages & Core



🚀 Signature Engineering

Autonomous Multi-Agent Market Research System

A sophisticated Tri-Agent Architecture focused on deterministic data retrieval and cross-verified research.

  • Design Pattern: Hierarchical Agent Teams (Librarian -> Quant -> Journalist).
  • Logic: Uses a RAG-based Librarian for semantic search, a Quant for numerical validation, and a Journalist for grounded synthesis to eliminate hallucinations.
  • Stack: LangGraph, Python 3.11+, Yahoo Finance API, FAISS.

Structured Data Extraction & Deployment Pipeline

An enterprise-grade system that performs high-fidelity metadata extraction from resume data to orchestrate a generative pipeline for interactive websites.

  • Architecture: Microservices (FastAPI) + Event-Driven Generation.
  • Tech: Groq (LLM Inference), PostgreSQL (State Management), Next.js (SSR Frontend).

Temporal Consistency Research in Computer Vision

An AI-powered translation system using computer vision to recognize hand gestures in real time. Focused on improving accessibility through a gesture recognition pipeline that converts temporal sign sequences into readable text.


📊 GitHub Engineering Metrics



"I don't just write code; I design systems."

Pinned Loading

  1. NeuroPath-ASD-Behavioral-Analytics NeuroPath-ASD-Behavioral-Analytics Public

    This project focuses on predicting the likelihood of an individual having Autism Spectrum Disorder (ASD) based on a series of behavioral traits and demographic information. The prediction is framed…

    Jupyter Notebook

  2. Carify-FullStack-FT-Transformer-Price-Predictor Carify-FullStack-FT-Transformer-Price-Predictor Public

    Carify is a full-stack machine learning application that predicts Car prices using a state-of-the-art FT-Transformer model (PyTorch). Built with Next.js 15 and Flask, it features a "Smart Search" e…

    TypeScript

  3. PokiDesk-AI-Sign-Language-Translator PokiDesk-AI-Sign-Language-Translator Public

    An AI-powered Sign Language Translator wrapped in a retro Pokedex UI. Converts real-time hand gestures into spoken audio with dual personality modes (Professional vs. Gen-Z) using MediaPipe, Groq L…

    Jupyter Notebook

  4. Twitter-Sentiment-Analysis Twitter-Sentiment-Analysis Public

    This project fine-tunes a pre-trained BERT model to classify the sentiment of tweets as either positive or negative and evaluates its performance.

    Jupyter Notebook 1

  5. AquaGuard-FullStack-Outbreak-Surveillance-System AquaGuard-FullStack-Outbreak-Surveillance-System Public

    AquaGuard is a comprehensive full-stack solution designed for municipal health departments to mitigate water-borne disease risks through data-driven insights. Unlike standard prediction models, thi…

    Jupyter Notebook

  6. AI-Financial-Research-Team AI-Financial-Research-Team Public

    An industrial-grade, multi-agent financial platform that orchestrates specialized AI researchers—including a RAG-based Librarian for document analysis, a Quant for technical indicators, and a Journ…

    TypeScript 1