AI Engineer · Full-Stack Developer · Founder, NeuraApp

I build intelligent products that solve real problems.

I'm Devesh — an AI engineer and product builder working across AI, web and mobile. I enjoy taking ideas from early concepts to products people can actually use.

AI EngineerLLMs, RAG & Agents
Full-Stack DeveloperNext.js, FastAPI & Python
Founder, NeuraAppInteractive AI Learning
Explore My Work →Let's ConnectAvailablefor select roles & advisory
Devesh Tiwari — AI Engineer & Founder of NeuraApp
that's me — building
AI & real products
About Me

An engineer who turns complex ideas into useful, real-world products.

I'm an engineer focused on the intersection of technical rigor and real user utility. I don't look at software as merely lines of code or closed tickets in a backlog; I view it as an asset that should solve genuine problems and survive real-world scale.

My work spans the full spectrum of modern product engineering: from architecting LLM workflows and RAG pipelines with strict source verification, to building high-performance Next.js and FastAPI backends, to publishing responsive cross-platform mobile apps with Flutter.

This commitment to practical problem-solving led me to found NeuraApp. Watching students struggle with passive video lectures convinced me that tech education must be hands-on — featuring in-browser code execution sandboxes and intelligent, Socratic AI mentorship.

DeveshAI Engineer & Founder, NeuraApp
Full-Stack
AI, Web & Mobile engineering across the complete product lifecycle.
NeuraApp
Founder & System Architect building interactive in-browser AI education.
Production
Deterministic retrieval, AST validation, and clean domain architecture.
Selected Work

Products that solved real problems

Each project represents hands-on engineering ownership — from problem formulation and system architecture to shipping production software users rely on.

AI & MLNeuraApp ● Live in Production
EdTech · AI Platform

NeuraApp — Interactive AI Learning Ecosystem

An AI-powered learning platform that helps developers and students master AI, ML, and software engineering through hands-on practice rather than passive video lectures.

Problem SolvedMost online tech courses are passive video tutorials with zero interactive feedback. Learners get stuck during local environment setup and lack real-time code evaluation or intelligent debugging assistance.
Actual ContributionConceived, designed, and built NeuraApp as founder and lead architect. Engineered the in-browser execution sandboxes, automated Abstract Syntax Tree (AST) validation test suite, and 'Ask Nea' — a lesson-aware Socratic AI mentor that guides learners without spoiling solutions.
Next.jsReactTypeScriptFastAPIPythonPyTorchDockerPostgreSQLTailwind CSS
MobileMx-Movie App ● Open Source
Mobile Engineering

Mx-Movie App — Cinema Discovery & Streaming Client

A cross-platform Flutter application for movie and TV discovery, trailers, and watchlist synchronization powered by the TMDB server API.

Problem SolvedMobile media discovery apps often suffer from sluggish image rendering, clunky navigation, and poor offline caching when handling high-density media feeds.
Actual ContributionDesigned and developed the entire Flutter application from scratch. Implemented efficient image caching, responsive layout adaptations for diverse screen densities, state management, and seamless trailer playback.
FlutterDartTMDB APIProviderSQLiteHTTP
Systems & ToolsAutomated File Organizer ● Open Source
Automation & Systems

Automated File Organizer — Intelligent Systems Utility

A Python utility that scans directories, classifies files by MIME types and creation metadata, and safely organizes cluttered filesystems with collision-proof timestamping.

Problem SolvedManual filesystem curation is tedious and error-prone, frequently resulting in overwritten files or fragmented storage across developer downloads and workspace directories.
Actual ContributionAuthored the Python automation engine with robust error recovery, recursive directory traversal, hash-based duplicate prevention, and automated classification rules.
PythonOS & ShutilMIME InspectionLoggingCLI
AI & MLEnterprise RAG & Knowledge Platform● Production Architecture
AI Architecture

Enterprise RAG & Knowledge Platform

Production-grade Retrieval-Augmented Generation architecture designed for zero-hallucination querying over multi-format technical documentation.

Problem SolvedStandard vector search fails on domain-specific acronyms and structured tables, while unconstrained LLMs hallucinate citations and leak outdated guidelines.
Actual ContributionArchitected a hybrid retrieval pipeline pairing dense embeddings with BM25 keyword matching, contextual reranking, structured chunk metadata, and strict inline source citation verification.
PythonFastAPIQdrantLangChainOpenAI & Claude APIDocker
Core Competencies

Areas of Expertise

A disciplined engineering foundation developed through production builds. No superficial logo walls — only disciplines and tools actively applied to build software that lasts.

Founder & Product Showcase

Building NeuraApp — making learning more personal.

Most technical education forces students into passive video consumption. When they finally write code, they hit environment setup hurdles, receive cryptic syntax errors, and struggle without instant feedback. NeuraApp is built around active, guided execution.

An AI-powered learning platform designed for real problem solvers.

NeuraApp transforms tech education into a personalized, hands-on experience. Learners write real code directly in sandboxed browser environments, receive instant Abstract Syntax Tree (AST) test verification, and learn with 'Ask Nea' — a lesson-aware Socratic AI mentor that explains concepts and nudges students forward without spoiling answers.

Role: Founder, System Architect & Full-Stack EngineerExplore NeuraApp Platform →
01

Hands-on Learning

Zero Local Setup

In-browser sandboxes for immediate coding

02

Evaluation

AST Verification

Automated syntax & logic test suites

03

AI Guidance

Ask Nea Mentor

Context-aware Socratic feedback

04

Curriculum

Core AI to LLMs

Structured engineering learning spines

Key Engineering Challenges Solved

Sandboxed Execution at Scale

Isolating untrusted user code execution in secure, low-latency container environments while delivering sub-second execution feedback.

Socratic AI Mentorship Without Hallucination

Prompt-engineering and grounding the 'Ask Nea' assistant with lesson context, test-case AST rules, and strict guardrails so it teaches principles instead of simply emitting copy-paste solutions.

Unified Learning Spines

Structuring a progressive learning graph starting from Python and linear algebra up through PyTorch, Deep Learning, RAG, and production LLM orchestration.

Track Record

Experience & Credibility

A chronological record of verified engineering contributions, technical leadership, and open-source public work.

2024 — Present · Remote / India
Flagship Venture

Founder & Lead Architect

Conceived and engineered an AI-powered interactive learning platform helping students and developers master AI, ML, and software engineering.

  • Designed and deployed the end-to-end platform using Next.js, TypeScript, FastAPI, and PostgreSQL.
  • Engineered automated in-browser code execution sandboxes with Abstract Syntax Tree (AST) test suites.
  • Built 'Ask Nea', a lesson-aware Socratic AI mentor that provides hints and conceptual debugging without spoiling answers.
  • Architected structured learning paths covering Python, math foundations, PyTorch, and LLMs.
2023 — Present · Global Remote
Engineering

AI & Full-Stack Engineer

Partnering with teams and building independent technology products spanning AI workflows, modern web platforms, and automated backend infrastructure.

  • Architected hybrid RAG pipelines using dense vector retrieval (Qdrant), keyword search (BM25), and source citation validation.
  • Developed full-stack web platforms using Next.js App Router, React, FastAPI, and Dockerized microservices.
  • Implemented automated data pipelines and systems utilities, such as the open-source Automated File Organizer.
  • Focused on system reliability, type safety, low latency, and maintainable software architecture.
2022 — 2024 · Remote
Mobile

Mobile Application Developer

Engineered responsive, cross-platform mobile applications for Android and iOS using Flutter and Dart.

  • Built and open-sourced Mx-Movie App, integrating TMDB REST APIs, local SQLite caching, and trailer streaming.
  • Engineered reusable widget systems, custom animation controllers, and responsive layouts across phone and tablet form factors.
  • Implemented offline-first state persistence, graceful error boundaries, and background data synchronization.
Writing & Insights

Technical Architecture & Product Thinking

Reflections from building NeuraApp, designing verifiable AI workflows, and scaling production software.

Start Here

Have an interesting problem to solve?

I'm always interested in thoughtful conversations, challenging engineering problems and meaningful collaborations.

Platform

Send a Message

Tell me what you are building, the problem being solved, or the technical collaboration you have in mind.