I'm an AI-focused Full-Stack and Backend Developer building practical GenAI products using Python, FastAPI, React, TypeScript, RAG, LLM tools, and AI agents.

I enjoy building systems where LLMs can retrieve knowledge, use tools, interact with databases, automate workflows, and power real-world applications.

Currently, I am focused on Agentic AI, RAG systems, LLM tool/function calling, full-stack AI products, and backend engineering.

• AI agents and tool-calling systems
• RAG applications with source-grounded responses
• Full-stack AI products with React, TypeScript, and FastAPI
• Backend APIs for LLM and data-driven applications
• Natural-language interfaces for databases and dashboards
• Applied machine learning and automation workflows

Languages: Python, JavaScript, TypeScript, SQL

AI / GenAI: LangChain, LangGraph, LlamaIndex, RAG, AI Agents, Tool Calling, LLM Applications

Backend: FastAPI, REST APIs, PostgreSQL, Supabase, SQLAlchemy, API Integration

Frontend: React, TypeScript, TailwindCSS, Recharts

Tools: Git, GitHub, Docker, ChromaDB, Pytest, Ruff, VS Code

A full-stack AI-powered business intelligence platform where users can connect databases, ask questions in natural language, generate SQL queries, and visualize results through dashboards.

Highlights:

• Natural language to SQL query generation
• AI-agent-based query reasoning workflow
• Database connection and dashboard management
• Interactive frontend visualizations

Tech: React, TypeScript, FastAPI, LangGraph, Supabase, Recharts, Groq/OpenAI-compatible LLMs

A RAG-based financial analysis system for SEC filings with document retrieval, table extraction, financial ratio analysis, and source-backed responses.

Highlights:

• Retrieves answers from financial documents
• Handles structured and semi-structured data
• Supports ratio-based financial reasoning
• Provides grounded responses with source context

Tech: FastAPI, LlamaIndex, LlamaParse, ChromaDB, Groq, React

A Python toolkit for building safe, reusable tools for LLM agents and function-calling workflows.

Highlights:

• Typed tool schemas using Pydantic
• Tool registry and executor
• Gemini function declaration adapter
• Utility tools for JSON, text processing, and local files
• Secret redaction and safer tool execution patterns

Tech: Python, Pydantic, Pytest, Ruff

A blockchain-based privacy-preserving IoT data transaction framework combining smart contracts, IPFS, encryption, access control, and ML-based pricing.

Highlights:

• Designed a secure IoT data-sharing workflow using blockchain and IPFS
• Implemented privacy-preserving access-control and revocation concepts
• Added CKKS-style error-bound reporting for encrypted computation reliability
• Used ML-based dynamic pricing for IoT data transactions
• Generated experimental results, ablation studies, and architecture diagrams

Tech: Python, Solidity, Ganache, IPFS, TenSEAL/CKKS, Machine Learning

• Building production-ready GenAI and full-stack AI applications
• Improving RAG pipelines and AI agent workflows
• Creating reusable LLM tools and function-calling systems
• Strengthening backend engineering with FastAPI, PostgreSQL, Docker, and testing
• Preparing for AI Engineer, GenAI Developer, Python Backend, and Full-Stack Developer roles

• GitHub: github.com/danishali778
• LinkedIn: linkedin.com/in/danish-ali-dev
• Email: danish.ali.73400@gmail.com