---
title: "About Shreyansh Kumar Singh — AI & Full-Stack Engineer"
description: "Shreyansh Kumar Singh is an AI & full-stack engineer in Pune, India. He builds AI-native systems — RAG pipelines, LLM agent loops and autonomous security tooling — on nearly four years of shipping production .NET, SQL Server and Angular software at RamanByte."
url: https://www.shreyanshkumarsingh.com/about
author: Shreyansh Kumar Singh
updated: 2026-10-08
---

# About Shreyansh Kumar Singh

Shreyansh Kumar Singh is an AI & full-stack engineer in Pune, India. He pairs nearly four years of production enterprise software at RamanByte Pvt. Ltd. with independent AI work — retrieval-augmented generation, LLM agent systems and autonomous security tooling — and writes down what a system must be before building it, then attacks it as an outsider would.

## Key facts

- **Role:** AI & Full-Stack Engineer
- **Based in:** Pune, Maharashtra, India
- **Current work:** Full-Stack Developer at RamanByte Pvt. Ltd. since January 2023 (Classroom+ LMS)
- **Education:** Bachelor of Technology (B.Tech), Computer Science, Dr. A.P.J. Abdul Kalam Technical University, 2017–2021
- **Open to:** Full-time or hybrid roles
- **Knows:** Retrieval-augmented generation, LLM agents, Multi-agent systems, Applied AI, Penetration testing automation, Full-stack web development, ASP.NET Core, C#, SQL Server, Angular, Next.js, React, TypeScript, Python, Flutter, Three.js, React Three Fiber, k6 load testing
- **Profiles:** [LinkedIn](https://www.linkedin.com/in/shreyansh-kumar-singh-080326205) · [GitHub (Shreyanskumarsingh20)](https://github.com/Shreyanskumarsingh20) · [X (@ShreyanshK98)](https://x.com/ShreyanshK98)

## Production work and independent AI projects

For nearly four years at RamanByte he has built the learning platform Classroom+ and client systems on top of it: a peer-reviewed journal portal, admin, student and faculty apps, and a two-app artisan marketplace launched on a fixed public date.

Alongside it he has built nine independent projects across nine domains: retrieval-augmented generation, autonomous security testing, AI quality assurance, 3D, physics simulation, editorial products, enterprise architecture and scroll-driven motion. The production work taught him what fails when real users arrive; the independent work is where he applies that lesson to newer problems.

## How he approaches a new problem

He starts with purpose: why the thing needs to exist and who is trying to get something done with it.

He treats complexity as a chain to be made legible — interface, API, logic, database, model, and the real world it touches.

He assumes failure. For the Dada Udyogini launch he designed DadaLoad, a distributed k6 load-testing system run across ten machines, so the team could prove capacity before launch day.

## AI engineering: RAG, agents and LLMs

Retrieval-augmented generation: in Sarthi, an AI relationship-manager copilot for banking, the pipeline is split into separately testable modules for embeddings, vector storage, retrieval and generation.

Agent systems: Nythera runs an LLM agent loop through a seven-phase penetration-testing workflow and confirms each finding with evidence; HallogenAI coordinates eight specialized agents to verify bug fixes against live application behavior.

Grounded products: BookVerse AI generates study guides grounded in the source text across several model paths, including local Ollama, and keeps running with no API key.

Responsible design: dangerous capabilities default to off (Nythera's internal-network scanning), and data provenance is enforced (Antarang uses only verified Wikimedia sources).

## How he specifies and audits his work

Almost every repository ships with a specification and a handoff document. After shipping, he audits his own work: the Sarthi audit ranks twenty findings from P0 to P3, worst first, and was published rather than quietly patched.

## Roles he is open to

Work where AI is load-bearing and correctness matters: document understanding, agent systems, security, and products that must survive real users. Open to full-time or hybrid roles in applied AI engineering, AI-focused full-stack engineering, security tooling, and senior .NET and Angular work.

## Career timeline

- **2017 – 2021 — B.Tech, Computer Science.** Dr. A.P.J. Abdul Kalam Technical University.
- **Jan 2023 — Joins RamanByte, Pune.** Full-stack developer on Classroom+: ASP.NET Web API, SQL Server, Angular and Flutter.
- **Oct 2023 – Mar 2024 — A Journal of Management (PIBM).** Rebuilt a hardcoded template into the live submission portal for a peer-reviewed journal (ISSN 2455-8796) — 93 commits.
- **At RamanByte — Classroom+ admin, student and faculty apps; Dada Udyogini.** Production apps for institutions, and a two-app Flutter marketplace launched on a fixed public date, load-tested beforehand with DadaLoad across 10 machines.
- **2026 — The range.** Sarthi, Nythera, HallogenAI, BookVerse AI, Antarang, The Collector's Pulse, The Evolution, VaultIQ and Revuelto — each with a written specification, most with an audit.
- **Aug – Sep 2026 — Vidur Industry Connect.** Admin dashboard, request lifecycle, near-duplicate guard and citizen profile suite on a multi-tenant Flutter + ASP.NET Core platform.

---

Shreyansh Kumar Singh — AI & Full-Stack Engineer, Pune, India. Contact: shreyanshkumarsingh208@gmail.com or https://www.shreyanshkumarsingh.com/contact (call and WhatsApp buttons). More: https://www.shreyanshkumarsingh.com/llms.txt · https://www.shreyanshkumarsingh.com/sitemap.xml
