# Sia Khorsand Software engineer. Studied Cognitive Science and Computer Science at UC San Diego, built Chalky, and was a founding engineer at Uniwise. HTML version: https://sia-khorsand.com/ - Resume: https://sia-khorsand.com/pdfs/Resume.pdf - LinkedIn: https://linkedin.com/in/siakhorsand - GitHub: https://github.com/siakhorsand - Email: skhorsand00@gmail.com - Agent guide: https://sia-khorsand.com/llms.txt ## About I'm Sia. I studied Cognitive Science and Computer Science at UC San Diego. I like working across a whole product, from deciding what to build to shipping it. I built [Chalky](https://chalky-app.com), a workout app I wanted for my own training. It's live on the App Store, and I own it end to end: design, development, launch, and growth. Before that, I was a founding engineer at Uniwise, building AI tools for organ-donation teams. I worked across the full stack, mostly backend and AI, plus AWS, and talked directly with the technicians who used it. An [interactive demo](https://sia-khorsand.com/src/uniwise-demo.html) recreates both products with fictional data. More on the [about page](https://sia-khorsand.com/about). ## Projects - [Chalky](https://sia-khorsand.com/src/chalky-case-study.html): 0 to 1 product, iOS. Gym log and form-check app, live on the App Store. - [Valet App Case Study](https://sia-khorsand.com/src/valet-business-app.html): field research, iOS. Valet operations app built from on-the-ground work at Best OC Valet. - [Revenue Manager Redesign](https://sia-khorsand.com/src/revenue-manager-redesign.html): product design case study. - [AI Product Recommender](https://sia-khorsand.com/src/ai-recommender-system.html): applied AI. Recommendation system using collaborative filtering and deep learning. - [DC-GANs Study](https://sia-khorsand.com/src/gan-study.html): applied research on deep convolutional generative adversarial networks. - [Uniwise: Call Copilot and ContraSight](https://sia-khorsand.com/src/uniwise-demo.html): interactive recreation of two healthcare AI products with fictional data. - [Shape Recognition CNN Canvas](https://sia-khorsand.com/src/shape-recognition-cnn.html): convolutional neural networks for computer vision. - [Clustering Visualization](https://sia-khorsand.com/src/clustering-visualization.html): interactive K-means demonstration. - [PathFinder Visualization](https://sia-khorsand.com/src/pathfinder-visualization.html): pathfinding algorithm visualization. - [Housing Market Forecast](https://sia-khorsand.com/src/housing-market-forecast.html): predictive modeling and data visualization. - [Multi-Agent Ball Game](https://sia-khorsand.com/src/multi-agent-ball-game.html): reinforcement learning agents. - [ML Algorithms Case Study](https://sia-khorsand.com/src/ml-algorithms-case-study.html): comparison of machine learning algorithms. - [Blackjack](https://sia-khorsand.com/src/blackjack-game.html): console game that grew into a Pygame interface. ## Skills and tools Grouped by the kind of work. Most of it comes from building Chalky and Uniwise. - AI and LLM systems: prompt engineering, structured outputs, agentic workflows, OpenAI and Gemini APIs, Google ADK, multimodal video analysis, OCR and document parsing, vector search, model evaluation, PyTorch. - Backend and data: FastAPI, REST APIs, WebSockets, Server-Sent Events, JWT auth (Auth0, Clerk), PostgreSQL, MongoDB, Supabase, row-level security, idempotency, S3. - Mobile and frontend: React, React Native, SwiftUI, StoreKit 2, HealthKit, offline-first sync, Material UI, HTML and CSS. - Product and design: user interviews, workflow mapping, rapid prototyping, UI/UX design, Figma, design systems. - Cloud and delivery: AWS (EC2, S3), Docker, Nginx, GitHub Actions, pytest, PostHog. - Languages: Python, TypeScript, JavaScript, SQL, Swift, C++. ## Experience ### Chalky, Founder and Product Engineer (February 2026 to present), Irvine, CA Founder and engineer behind Chalky, a gym log and form-check app live on the App Store. It turns free-form workout notes into structured data, insights, and coaching, and reviews lift form from video. I own it end to end: research, product, design, engineering, launch, and support. - Ran a TestFlight beta with more than 60 testers, then reworked onboarding, logging language, and failure states based on where they got stuck. - Shipped to the App Store and handle user support directly. - Built the native iOS app, Supabase backend, and offline-capable sync layer. - Designed a coaching loop where policy code owns scoring and safeguards, while models handle interpretation and drafting. - Added structured outputs, provider failover, idempotency, caching, and server-side quotas so failures stay recoverable. Worked with SwiftUI, SwiftData, Python, Supabase, Clerk, and structured LLM outputs. ### Uniwise, Founding Full-Stack Engineer (May 2025 to February 2026), La Jolla, CA One of the first three engineers. I took two donation-support products from technician interviews to deployed MVPs: a live call copilot, and ContraSight, which screens donor records for contraindications. Full stack, leaning toward backend and AI. - Interviewed donation technicians, mapped how their calls and record reviews actually run, and decided what to build first. - Live call copilot: a Recall.ai bot joins the call, transcripts stream to the screen over WebSockets with speaker labels, and MongoDB keeps each call's state tied to its case. - ContraSight: Marker, PyMuPDF, and Tesseract read scanned records, then Gemini checks 71 contraindications. Every finding cites the exact text, highlighted in an annotated PDF. - FastAPI services behind both products: Auth0 JWT auth, per-organization scoping, AES-256 encrypted S3 storage, and Server-Sent Events for live progress. - React and TypeScript front ends, including the reviewer where each finding jumps to its source text. Deployed ContraSight with Docker and Nginx on AWS. Worked with Python, TypeScript, FastAPI, React, WebSockets, Server-Sent Events, MongoDB, S3, Auth0, Recall.ai, Marker, Tesseract OCR, and Gemini. ### UC San Diego, Instructional Assistant, Cognitive Science (September 2024 to June 2025), La Jolla, CA Helped teach two Cognitive Science courses and supported more than 100 students through labs, discussions, office hours, and project feedback. - COGS 150: Large Language Models and Cognitive Science - COGS 10: Cognitive Consequences of Technology Covered transformers, PEFT/LoRA, prompt engineering, Python, and project feedback. ## More pages - [About](https://sia-khorsand.com/about) - [Contact](https://sia-khorsand.com/contact) - [Privacy](https://sia-khorsand.com/privacy) - [Sitemap](https://sia-khorsand.com/sitemap.xml)