Skip to content
Arian Khademi

Work

Projects

Things I designed and built end to end. Each one started as a problem I actually had, and a couple turned into pitches.

AI classroom and learning ecosystem

  • TypeScript
  • React
  • Node.js
  • OpenAI API
  • Built student and teacher dashboards with grade management, real-time discussion, and assessments generated from uploaded course materials.
  • Built an OpenAI-powered tutoring assistant that supports student comprehension while reducing direct answer replication and low-effort AI misuse.
  • Shipped a professor toolkit that turns uploaded PDFs and textbooks into rubrics, assessments, and generated course content.
Read the full write-up

Nestd

2026

AI-native, direct-to-landlord rental platform for the GTA

  • Next.js
  • TypeScript
  • Node/Express
  • PostgreSQL
  • Prisma
  • Claude
  • Stripe
  • Clerk
  • Built the full-stack platform as a Turborepo monorepo spanning web, API, and shared packages, running the entire rental loop (browse → AI-screen → lease → rent collection) end to end and designed to cut agent commissions out of the deal.
  • Built 9 Claude-powered AI services (applicant match scoring, natural-language listing search, listing-description generation, roommate compatibility, student/newcomer screening), each with a deterministic heuristic fallback so the product still runs without API keys.
  • Built student- and newcomer-friendly screening (a built-in guarantor flow, no Canadian credit history required) plus AI-assisted Ontario RTA lease and LTB notice generation with rent-cap auto-checks.
  • Wired up Stripe (test mode) for rent and paid-service flows, Clerk auth, Pusher real-time messaging, Mapbox, and a verification layer with government-ID and proof-of-ownership checks.
Read the full write-up

Multi-tenant AI sales-automation platform

  • Next.js
  • TypeScript
  • React
  • Claude
  • Structured Outputs
  • RAG
  • Built a multi-tenant lead-intake app that ingests inquiries from web forms, email, and call notes and returns structured qualification, a summary, a drafted reply, routing, and a next task in a single Claude call.
  • Used JSON-schema-constrained structured outputs to pull contact fields and classify lead quality (hot/warm/cold/spam) without hallucinated data, keeping API keys server-side behind route handlers.
  • Built a per-client config layer injected into the system prompt, so qualification logic, routing, and reply tone adapt per business with no code changes.
  • Extended it into a full pipeline (deal stages, value tracking, stale-deal detection, an LLM follow-up generator) plus real-time live-call transcription that surfaces suggested responses mid-call.
Read the full write-up

Algorithmic modeling and data-engineering platform

  • Python
  • NumPy
  • pandas
  • Genetic Algorithms
  • Bayesian Optimization
  • Built a streaming ETL pipeline that processes a 56 GB CRSP market-data set row-by-row in constant memory, applying split/dividend adjustments and emitting clean per-symbol data for backtesting.
  • Engineered a composable strategy layer searched by a genetic algorithm and Bayesian optimization, and implemented gradient-boosted-tree and Q-learning models from scratch in NumPy.
  • Built a walk-forward validation gate (out-of-sample testing, purged cross-validation, transaction-cost modeling) that keeps strategy selection and validation strictly separated.
  • Designed, built, tested, and operated the whole platform solo, backed by 260 automated tests run as a pre-merge gate with safety guarantees encoded as executable invariants.
Read the full write-up

LLM assistant for financial documents

  • React
  • FastAPI
  • PostgreSQL
  • pgvector
  • OpenAI API
  • Docker
  • Built an LLM assistant that ingests annual reports, earnings transcripts, and investor materials and answers analyst-style questions with cited source passages.
  • Implemented the full RAG pipeline (document parsing, chunking, embeddings, semantic search over PostgreSQL/pgvector, and OpenAI responses) with 'insufficient context' answers when the documents don't support a claim.
  • Built an evaluation harness measuring retrieval quality, hallucination risk, and answer consistency, and containerized the whole stack with Docker Compose behind CI/CD checks.
Read the full write-up

Wagr

2024

Probabilistic forecasting and a play-money prediction market

  • Python
  • PyTorch
  • Perplexity API
  • Built a probabilistic forecasting system for a friends-based, play-money prediction game, combining historical event data, live odds, and market signals into event-probability estimates.
  • Trained a custom PyTorch model to fold historical patterns and external market signals into a single calibrated probability.
  • Built peer-to-peer and global prediction markets (market creation, odds updates, and AI news summaries via the Perplexity API), plus an engagement layer of streaks, XP, daily quests, and a leaderboard with head-to-head duels.
Read the full write-up

Knock

2025

Real-time social audio/video app

  • React Native
  • LiveKit
  • WebRTC
  • Built a real-time social audio/video mobile app (live rooms, participant presence, and low-latency communication) with React Native and LiveKit.
  • Implemented room discovery, session joining, user profiles, and live interaction flows for a Clubhouse/Houseparty-style experience.
  • Leaned on LiveKit for the real-time transport and participant state, and spent my effort on the mobile-first room experience built on top of it.
Read the full write-up