Harsh.ai

Available for opportunities

Agentic AI
Developer

Building autonomous AI systems, RAG pipelines, and structured LLM workflows from scratch in Python — deliberate framework usage, full architectural control.

6
Projects Built
~30ms
RAG Latency
~80%
API Calls Saved
8+
Months Eng. Exp
View Projects Download Resume Let's Talk
harsh@dev:~$
$ python -c "import harsh; harsh.introduce()"
Initializing Harsh Bhanushali — Agentic AI Developer...
✓ Agentic AI: Autonomous systems, RAG, LLM Orchestration
✓ AI Stack: Groq API, Gemini API, ChromaDB, LangChain, LangGraph, MCP
✓ APIs & UI: FastAPI, Streamlit, DuckDuckGo, Tavily
✓ CLI Tools: Rich, Python, JSON storage
✓ Backend: ASP.NET (C#), SQL Server, HTML/CSS/JS
$ harsh.currently_learning()
> ["FastAPI", "Docker", "Ollama (local models)"]
$ harsh.get_availability()
> "Open to AI Engineer roles | Entry-level | Remote-friendly"

About Me

I'm an Agentic AI Developer who builds autonomous AI systems in Python — using frameworks deliberately and purposefully, with full understanding of every architectural layer underneath.

My focus is on RAG pipelines, LLM orchestration, and cost-aware AI design. I also have hands-on production experience building enterprise web applications during my full-stack engineering internship — shipping 3 apps, improving workflow efficiency by 30%, and rebuilding a complete system under live client requirements.

"I use frameworks deliberately — always understanding the layer beneath before I abstract it away."

Agentic AI Systems
Autonomous agents from scratch
RAG & Vector Search
ChromaDB · SentenceTransformer
CLI Engineering
Python · Rich · Modular design
Full-Stack Backend
ASP.NET · SQL Server · REST

Featured Projects

Production-ready applications demonstrating advanced Python, AI/ML, and system design skills

hArI

RAG Document Intelligence · Deployed
RAG Streamlit

Production-ready document intelligence app — upload PDFs, ask questions, get cited answers. Cosine similarity filtering ensures only semantically relevant chunks reach the LLM.

ChromaDB cosine similarity with configurable score threshold
PyMuPDF + sentence-transformers (all-MiniLM-L6-v2) pipeline
Groq (llama-4-scout-17b) · Source citation deduplication
Python • Streamlit • ChromaDB • Groq API

Multi-Agent Research Pipeline

Agentic Research System · Shipped
Agents Groq

6-agent autonomous research pipeline — Supervisor, Search, Scraper, Summarizer, Critic, Synthesizer — with complexity-based model routing and quota-aware fallback between Groq and Gemini.

Groq (llama-3.3-70b) primary · Gemini (gemini-3-flash-preview) fallback
DuckDuckGo search + web scraping per query
CLI displays which model handled each agent in real-time
Python • Groq API • Gemini API • Rich CLI

AI Agent Engine

Autonomous AI System · Shipped
RAG LLM

Production-grade autonomous agent — 4-layer pipeline (cache → pattern router → RAG → LLM) routing ~80% of queries with 0 LLM calls. Per-session cost ~$0.0005.

ChromaDB + SentenceTransformer RAG with ~30ms latency
Cost-aware token tracking & daily quota enforcement
Planner → Validator → Executor → Responder pipeline
Python • Gemini API • ChromaDB • SentenceTransformer

Finance Agent (CLI)

CLI Finance System · Shipped
CLI Groq

Standalone CLI finance agent supporting 8 natural-language commands — built on top of Expense Tracker's classes with zero code duplication, reducing development effort by ~60%.

8 commands: add, update, delete, summaries, dashboard
Per-category monthly budget tracking with real-time status
Groq-powered NLP layer · fully offline fallback
Python • Groq API • OOP • CLI

NextSteps

AI Career Planning App · Shipped
FastAPI LLM

AI career planning app that analyzes a resume against a job description or URL — delivers full gap analysis, skill mapping, and personalized roadmap in under 5–8 minutes. Clean separation between parsing, analysis, and output generation with no hardcoded assumptions about resume or job format.

Resume vs JD gap analysis with skill mapping
URL-based JD parsing — no manual copy-paste
Modular pipeline: parse → analyze → output
Python • FastAPI • Groq API • Tavily

DevMind — MCP Server

MCP Tool Server · Shipped
MCP HITL

A local MCP server exposing 6 developer tools — file ops, Python execution, and JSON utilities — with human-in-the-loop confirmation built into any action that writes or runs code.

6 tools: read_file, write_file, list_directory, run_python_snippet, format_json, count_tokens
HITL guardrails on write and run — no side effects without explicit confirmation
Solved subprocess stdin isolation bug that silently breaks naive MCP implementations
Python • MCP SDK • tiktoken • uv
View All Projects on GitHub

Technical Expertise

Production-proven skills across the full Python ecosystem and modern AI/ML stack

Core Specializations

Agentic AI

Autonomous systems built from scratch

• RAG, LLM Orchestration, Tool-Calling
• Groq API, Gemini API, ChromaDB
• Cost-aware AI design

CLI Engineering

Modular Python CLI systems

• Python, Rich, JSON storage
• OOP, modular architecture
• Session management, auth

Full-Stack Backend

Enterprise web applications

• ASP.NET (C#), SQL Server
• HTML, CSS, Bootstrap, JS
• Crystal Reports & dashboards

Technology Stack

Python
Intermediate+
SQL
Proficient
JavaScript
Familiar
ChromaDB
RAG / Vector
Groq API
LLM Layer
Streamlit
AI UIs
FastAPI
Backend APIs
LangChain
LLM Chains
LangGraph
Agent Graphs
MCP
Tool Servers
Git / GitHub
Version Control

Certifications & Recognition

B.E. Information Technology
GEC Modasa · 2024
GATE 2025 Qualified
Computer Science Engineering (CSE)

Let's Build Something Amazing

Entry-level AI Agent Engineer open to full-time roles and internships at AI-first startups. Let's build something real together.

Open to Opportunities

Looking for entry-level AI Engineer, ML Engineer, or Python Developer roles at AI-first startups.

Get In Touch

Open Source & Collaboration

Interested in contributing to open source projects or technical partnerships.

View GitHub
harshbhanu0709@gmail.com
Gujarat, India · Open to Remote
Available immediately