Disha Faujdar — Software Engineer & AI Practitioner. Portfolio and projects.

Disha's workstation

Hey, it's I & kiu (she's the senior engineer 🐱)

Disha Faujdar, an engineer from, India. Currently working at no where, I build things that put me in flow — code, content, whatever pulls me in.

Location:India
Experience:~1 years
Role:Software || AI/ML Engineering

Experience

Software Engineer (Fulltime) — Superset
March 2025 — March 2026

Built an AI-powered health tracking mobile app with Expo, Supabase, and PostgreSQL. Improved screen load times by ~35% via soft reloading, client-side caching, and incremental state updates. Enhanced in-app search with prefix-based and fuzzy matching, improving successful search results by ~45%. Tech: Expo, Node.js, Prisma.

Software Engineer (Freelancer) — US Based Startup
July 2025

Developed a full-stack inventory management system using Next.js, React, and TypeScript. Improved data retrieval performance by ~40% through normalized schemas and indexed queries. Reduced manual inventory tracking errors by ~60% with automated stock updates and validation logic. Tech: React.js, Node.js, Prisma.

Projects I've worked on:

NewFillit
2026

Fillit is a job application autofill system: a Next.js dashboard to manage your profile and resumes, a Chrome extension that fills application forms using a native setter strategy cascade, and a Node/Express API with PostgreSQL.

NewWikiMind - RAG
2026

WikiMind — full-stack RAG system where users upload PDFs and chat with their documents. Built adaptive retrieval hybrid BM25 + reranking based on corpus size, hierarchical chunking, streaming responses, used async pipelines, redis and bull.js for queuing and background jobs, and end-to-end observability via Langfuse.

Synthesia — AI Research Agent
2025

AI Research Agent that accepts a topic, runs a small research workflow, and returns a structured result. Tech: TypeScript, Redis, Bull.js, Express, PostgreSQL.

OSS-Align
2025

Conservative decision system matching developers with realistic open-source contribution opportunities. Analyzes proven work history and matches with contributor-friendly repos. Tech: Python, Typer, Rich, GitHub API, Sentence Transformers, FAISS, LLMs.

Trainyard
2024

Interactive web app for experimenting with ML models. Real-time training and visualization over WebSockets with PyTorch and FastAPI.

MiniKit
2023

Scikit-learn built from scratch in NumPy to understand ML algorithms at their mathematical core.

In progressMnemo
2026

A production-grade memory middleware REST API for AI agents. Mnemo gives stateless LLMs (GPT, Claude, coding assistants) persistent, temporally-aware memory by maintaining three memory layers: episodic (raw), semantic (structured facts with bi-temporal edges), and a user profile. It is inspired by Mem0's fact extraction pipeline and Zep/Graphiti's bi-temporal edge model, but implemented without a graph database — using SQLite + Qdrant only, keeping it lightweight and self-hostable.

Lab

Experiments & exploration.

Problems I can solve

Systems & Scale: Distributed Systems, Horizontal Scaling, Load Balancing, Message Queues, Event-Driven Architecture, Caching Strategies, Database Sharding

Real-Time & Async: WebSocket Systems, Job Queues & Workers, Stream Processing, Async/Concurrent Design

AI & ML Engineering: LLM Integration, RAG Pipelines, Vector Search

Backend & APIs: REST API Design, Auth Systems, Rate Limiting

DMs open. Coffee first. ☕
Reach me at dishafaujdar.work@gmail.com.

Handles

XGithubLinkedInYouTubeFiverrResume