Skip to content
View Nareshdevelop's full-sized avatar
  • Prosper, TX

Block or report Nareshdevelop

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
Nareshdevelop/README.md

Hi, I'm Naresh Kallepalle 👋

Senior Full-Stack & AI Product Engineer — I take ambiguous problems from idea to shipped, production software. 14+ years across federal healthcare and regulated systems, now building production LLM applications end-to-end.

📍 Prosper, TX · ✉️ nkumarkallepalle@gmail.com · Open to Full-Time / C2C opportunities.

What I build

  • AI / LLM products — multi-agent orchestration, RAG, deterministic structured outputs, and automated evaluation & quality gating on the Anthropic & OpenAI APIs.
  • Full-stack systems — React 18 + TypeScript, .NET 8 / ASP.NET Core / C#, Python, SQL Server / PostgreSQL, REST & Minimal APIs, OAuth2 / OIDC.
  • The whole thing — architecture → code → CI/CD → cloud (DigitalOcean / Azure, nginx / Linux) → 24/7 production support. I've shipped and operate live SaaS solo.

Featured work

Project What it is
fivedaylaunch · case study Live, multi-region AI website builder — a one-sentence-to-multi-page-site agent flow on the Claude API, with an 8-dimension quality scorer + CLI quality gate and a 1,935-site regression corpus. Full product: 24-page portal, mobile editor, Stripe / Razorpay billing, JWT + 2FA auth.
Clinical Dictation AI Pipeline End-to-end medical speech-to-text: VAD → Whisper / faster-whisper ASR → clinical NLP (medspaCy), scored on Word Error Rate + clinical-concept accuracy, with a human-in-the-loop review editor (audio-synced transcript, drug/dose/negation flags, sign-off gate).
fdl-mcp-server Model Context Protocol server that lets Claude / Cursor audit any website — practical AI tooling, no API key required.
Relvexa Claude-powered agents automating medical-billing workflows, with Availity eligibility integration.
ai-learning ML foundations from scratch in Python / NumPy — gradient descent, linear regression, and neural-network building blocks by hand.

Tech

Python · TypeScript · React · .NET / C# · Node.js · Anthropic Claude API · OpenAI API · RAG · SQL Server · PostgreSQL · Azure · DigitalOcean · nginx · Linux

Reach me

📧 nkumarkallepalle@gmail.com · 💼 LinkedIn · 🌐 fivedaylaunch.com

Senior full-stack engineer who ships AI products end-to-end. Healthcare · regulated systems · applied GenAI.

Popular repositories Loading

  1. ai-learning ai-learning Public

    ML foundations from scratch in Python/NumPy - gradient descent, linear regression, and neural-network building blocks by hand.

    Python

  2. fdl-site-audit fdl-site-audit Public

    Free, deterministic, zero-dependency website audit library. 5-pillar scoring. Powered by fivedaylaunch.com.

    JavaScript

  3. fdl-mcp-server fdl-mcp-server Public

    MCP server for fivedaylaunch.com - lets Claude audit, compare, and check AI-visibility of any small business website. No API key required.

    JavaScript

  4. awesome-mcp-servers awesome-mcp-servers Public

    Forked from punkpeye/awesome-mcp-servers

    A collection of MCP servers.

  5. awesome-mcp-servers-1 awesome-mcp-servers-1 Public

    Forked from wong2/awesome-mcp-servers

    A curated list of Model Context Protocol (MCP) servers

  6. fdl-chrome-extension fdl-chrome-extension Public

    Free Chrome extension showing the fivedaylaunch quality score (Performance, SEO, Mobile, Security, AEO) for any small business website. Powered by fivedaylaunch.com/api/audit.

    JavaScript