Skip to content
View shubh9119's full-sized avatar

Block or report shubh9119

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
shubh9119/README.md

πŸš€ Featured Production AI & LLM Systems

Project Domain & Architecture Core Stack
πŸŽ™οΈ voice-ai-low-latency-agent Real-Time Low-Latency Voice AI Agent & Speech RAG Pipeline (Sub-380ms TTFA) Python WebRTC Whisper LoRA (STT) Streaming TTS Qdrant
πŸ₯ clinical-ai-medical-rag-assistant Clinical AI Scribe, Multimodal Medical Imaging Diagnosis & HL7 FHIR R4 / SOAP System Python Medical VLM FHIR R4 ICD-10 NER Safety Guardrails
πŸ”„ agentic-rag-langgraph-pipeline Stateful Corrective & Hybrid Agentic RAG with Reciprocal Rank Fusion (RRF) LangGraph Qdrant Hybrid RRF Claude Sonnet FastAPI
βš’οΈ multi-agent-mcp-orchestrator Multi-Agent LLM Orchestration Platform with Model Context Protocol (MCP) Server Bus MCP Multi-Agent Anthropic Tool-Use JSON-RPC 2.0 Docker
⚑ llm-finetuning-eval-pipeline 4-Bit QLoRA / LoRA SFT Post-Training Pipeline & Automated CI/CD Quality Gate PEFT / LoRA TRL SFTTrainer P01-P12 Diagnostics GitHub Actions

πŸ‘‹ Hi, I'm Shubham Singh

πŸ€– Autonomous AI Agent Engineer & Full-Stack Developer

GitHub Followers Email LinkedIn


πŸš€ Building Production AI Agent Harnesses β€’ Native LLM Tool-Calling Pipelines β€’ Scalable Full-Stack Systems

πŸ‘¨β€πŸ’» About Me

I am a software engineer specializing in Autonomous AI Agents, Generative AI systems, and full-stack architecture. I build robust, production-grade agentic harnesses from first principlesβ€”combining multi-turn ReAct reasoning loops, dynamic tool reflection, and durable memory layers with high-performance Python and MERN backends.

  • πŸ”­ Current Focus: Autonomous AI Receptionists, Multi-Agent Coordination, and Scalable Full-Stack SaaS Platforms.
  • 🧠 Specialized In: ReAct Agent Loops, LLM Function Calling, Dynamic Schema Generation, and Durable Memory Stores.
  • ⚑ Core Engineering Values: First-principles design over framework bloat, defensive error handling, and 100% deterministic testability.
  • πŸ’¬ Ask Me About: AI Agent Architectures, Python / FastAPI, MERN Stack (React, Node, Express, MongoDB), and REST APIs.

πŸ› οΈ Technical Arsenal

Category Technologies & Tools
AI & Agentic Systems Google Gemini API β€’ OpenAI GPT-4o β€’ Ollama β€’ ReAct Agent Loops β€’ Function Calling β€’ Prompt Engineering
Backend Engineering Python β€’ FastAPI β€’ Node.js β€’ Express.js β€’ REST APIs β€’ Pydantic β€’ httpx β€’ WebSockets
Frontend Development React.js β€’ JavaScript (ES6+) β€’ TypeScript β€’ HTML5 / CSS3 β€’ Tailwind CSS β€’ Redux
Databases & ORM PostgreSQL β€’ MongoDB β€’ Redis β€’ SQLite β€’ Mongoose β€’ SQLAlchemy
DevOps & Testing Docker β€’ Docker Compose β€’ Git / GitHub β€’ pytest β€’ CI/CD Pipelines β€’ Linux

🌟 Flagship Project (Top Spotlight)

Production-Grade AI Receptionist built from First Principles (Zero Framework Bloat)

Python FastAPI Gemini Pytest License

An autonomous AI receptionist capable of conversational table bookings, real-time availability checks,
dietary filtering, food pre-ordering, and personalized recommendations using durable customer memory.
  • πŸ”„ Autonomous ReAct Loop: Multi-turn reasoning engine that safely chains availability checks, table bookings, and food orders in sequence.
  • πŸ› οΈ 16 Specialized Tools: Python reflection decorator (@tool) that dynamically generates schemas from type hints with defensive fault recovery.
  • 🧠 Durable Memory Engine: Persists customer preferences (seating, allergies, favorites) and past order history into the backend database.
  • πŸ§ͺ 100% Deterministic Testing: 56 unit tests utilizing StubLLM and MockAPI fixtures running in <0.4s with zero real LLM costs.

πŸ“‚ Other Notable Projects

A full-stack AI SaaS application featuring modern UI components, subscription billing workflows, and generative AI integrations for automated content workflows.

  • Full-stack React + Node.js architecture
  • Secure API authentication and modular services

🌦️ Weather App

Real-time meteorological web application consuming dynamic weather APIs to deliver accurate climate forecasts, temperature metrics, and geolocation lookups.

  • Asynchronous HTTP API fetching with error handling
  • Clean, responsive interface optimized for all screens

Cryptographic utility for generating highly secure, customizable passwords with entropy controls (symbols, digits, casing, length) and one-click clipboard copy.

  • Client-side cryptographic randomness
  • Custom complexity rules and instant validation

A collection of web applications, REST backend services, and algorithmic problem-solving implementations built with clean code and modern standards.

  • Scalable MVC backends with Express & MongoDB
  • Reusable React components and state management

πŸ“Š GitHub Analytics

Shubham's GitHub Stats Top Languages

πŸ“¬ Get in Touch

Gmail GitHub

Open to AI Engineering roles, freelance agent development, and high-impact full-stack opportunities.

Β© 2026 Shubham Singh. Crafted with precision & clean architecture.

Popular repositories Loading

  1. llm-finetuning-eval-pipeline llm-finetuning-eval-pipeline Public

    End-to-End LLM SFT / LoRA Fine-Tuning Pipeline & Automated CI/CD RAG Failure Diagnostics Quality Gate

    Python 1

  2. clinical-ai-medical-rag-assistant clinical-ai-medical-rag-assistant Public

    Clinical AI Scribe, Multimodal Medical Imaging Diagnosis & FHIR/SOAP Healthcare RAG Decision Support System

    Python 1

  3. voice-ai-low-latency-agent voice-ai-low-latency-agent Public

    Real-Time Low-Latency Voice AI Agent & Speech RAG Pipeline (STT / TTS / WebRTC / Qdrant) with sub-380ms TTFA optimization

    Python 1

  4. multi-agent-mcp-orchestrator multi-agent-mcp-orchestrator Public

    Multi-Agent LLM Orchestration Platform with Model Context Protocol (MCP) Server Routing, Tool Namespacing, and Loop Guards

    Python 1

  5. agentic-rag-langgraph-pipeline agentic-rag-langgraph-pipeline Public

    Stateful Agentic & Corrective Hybrid RAG System built with LangGraph, Qdrant, Reciprocal Rank Fusion (RRF), and Self-Reflection

    Python 1

  6. shubh9119 shubh9119 Public

    Config files for my GitHub profile.