Skip to content

Student · Founder · Engineer

Xavion Mirchandani

I build AI products and the systems around them

I'm a high-school student at Blair Academy, class of 2029. At 13 I built Xavion AI, a multi-model AI platform. In the summer of 2026 I interned as a software engineer at Preface in Singapore, where, as the only engineer on the local team, I shipped production AI agents and built the company's internal CRM.

View projectsAbout me
Xavion Mirchandani

01 — Experience

Where I’ve worked

  1. Jun 2026 – Aug 2026

    Singapore

    Preface — Software Engineering Intern

    Sole engineer on the Singapore team of Preface, a global technology-education company — built agentic automation and internal tooling that went into production for real client outreach.

    • Built and ran a production multi-agent pipeline in Python that automates client outreach end-to-end: an outreach agent that drafts personalized emails with AI-researched company backgrounds, a scheduling agent that classifies reply threads and flags follow-ups, and a calendar-sync agent that reconciles Google Calendar with color-coded client statuses.
    • Designed and shipped Preface 2559, the company's internal CRM platform — a Prospect → Won pipeline with a drag-and-drop board, per-business timelines, and a human confirm queue that gates every outward-facing agent action. Deployed at preface.sg.
    • Hardened the platform for production: database migration baselines with CI, row-level security, a durable action executor with idempotency keys and full audit trails, and an agent evaluation suite of 40 fixtures including prompt-injection attacks.
    • Built a tender scanner that scrapes GeBIZ (Singapore's government procurement portal) and uses Gemini to score and rank open tenders against company fit, replacing a weekly manual trawl.
    • Merged five fragmented client lists into a single deduplicated master dataset of ~700 records, and assisted as a teaching assistant at the Preface International Summer Program.
    • Python
    • TypeScript
    • Next.js
    • Supabase
    • PostgreSQL
    • Gemini API
    • Google Workspace APIs
    • Vercel

  2. Feb 2025 – June 2026

    Singapore

    Xavion AI — Creator & Sole Developer

    Designed and built a multi-model AI platform that brings 30+ models into one interface. Completed in June 2026; no longer under active development.

    • Designed a unified abstraction layer over multiple AI provider APIs (OpenAI, Anthropic, Google, and others), normalizing authentication, request formats, and response structures.
    • Implemented real-time streaming with Server-Sent Events and side-by-side conversations with up to six models at once, plus image generation and prompt refinement.
    • Next.js
    • React
    • TypeScript
    • SSE
    • Provider APIs

02 — Projects

Featured projects

Xavion AI

AI platform · Sole Developer

A multi-model AI platform that brings 30+ models together in one place, supporting side-by-side conversations with up to six models, response comparison, and image generation in one unified interface.

  • Next.js
  • TypeScript
  • SSE streaming
  • 30+ models
Visit Xavion AI

Preface 2559

CRM platform · Preface internshipSummer 2026

An AI-driven CRM platform built for Preface during my internship. Custom agents manage the entire client pipeline, classifying each business, updating its timeline, and proposing next actions as deals progress, while client-facing actions are gated behind human approval. The platform runs in production at the company.

  • Next.js
  • TypeScript
  • Supabase
  • PostgreSQL
  • Gemini API
About Preface

Home Lab Server

Home server · Personal project

A 360TB home server designed and built from parts, hosting a full media library, game servers, and a stack of self-hosted services. The server consists of eighteen drives and is arranged with enough redundancy to survive multiple simultaneous drive failures without any data loss.

  • TrueNAS SCALE
  • ZFS
  • 360TB storage
  • Self-hosted
Visit the server homepage

Personal Investment Portfolio

Stock portfolioSince 2022

A real-money portfolio I have managed myself since I was 10, using a core-and-satellite strategy: high-conviction mega-cap tech held on a ten-year horizon, alongside smaller positions I trim, add to, and rotate. Every buy, sell, and dividend on the dashboard includes my reasoning, including the trades that went badly.

  • Investing
  • Every trade explained
  • Live market data
View the dashboard

Big Two AI

Card game AI · Personal project

An AI that taught itself the card game Big Two through more than 30 million deals of self-play, built on a DouZero-style deep neural network trained with no human games to imitate. Both the trained network and a second, odds-based engine are available as fully playable opponents.

  • Python
  • C
  • Monte Carlo
  • Deep RL
Play Big Two

Mahjong Hand Analyzer

Hand analysis engine · Personal project

An app that reads a 14-tile Mahjong hand, typed or photographed, and ranks the closest winning hands in under a second. Each hand is evaluated against more than 21 million possible winning combinations, accounting for jokers, exposed tiles, and every tile already visible on the table.

  • C
  • Python
  • React Native
Google Play— coming soonApp Store— coming soon
All projects

03 — Contact

Get in touch