About

I'm Sia, a Cognitive Science student at UC San Diego with a minor in Computer Science. I like working across the whole product, from the interface and data model to the backend and the parts that use AI.

I'm building Chalky, a workout app that started as something I wanted for my own training. I've built the iOS app, backend, sync system, and coaching pipeline. I test it with lifters, interview users, and use their feedback to decide what is actually useful.

Before that, I helped build software for organ-donation teams at Uniwise. That work brought together backend engineering, document processing, applied AI, and careful workflow design in a setting where people needed to verify every result.

Projects

Skills & tools

How I move from ambiguous workflows to deployed, measurable systems.

Product discovery & delivery

Customer interviews, workflow mapping, problem framing, MVP scoping, technical requirements, rapid prototyping, prioritization, stakeholder alignment, launch planning, and feedback loops.

Backend & integrations

Python, TypeScript, SQL, FastAPI, REST APIs, WebSockets, PostgreSQL, MongoDB, Supabase, Redis, S3, and third-party integrations.

Applied AI systems

Structured outputs, LLM workflows, RAG, vector search, multimodal pipelines, human-in-the-loop controls, model evaluation, PyTorch, and scikit-learn.

Deployment & reliability

Authentication, row-level security, idempotency, testing, CI/CD, Docker, observability, quotas, provider failover, and production rollout.

Experience

Chalky

- Present

Irvine, CA

Founder & Product Engineer

I started Chalky to make workout logging feel as natural as writing a note. The app is now in TestFlight with active testers.

  • 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

-

La Jolla, CA

Founding Software Engineer

I was one of the first three engineers, working directly with donation technicians on a live-call copilot and a clinical document review tool.

  • Built a live referral-call pipeline with speaker-aware transcription and case-scoped state.
  • Led a clinical document pipeline that preserved page references for 71 contraindication checks.
  • Built the FastAPI services, organization scoping, encryption, and progress streaming behind both products.

Worked with Python, FastAPI, WebSockets, MongoDB, PostgreSQL, OCR, and RAG.

UC San Diego

-

La Jolla, CA

Instructional Assistant, Cognitive Science

I 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 & Cognitive Science
  • COGS 10: Cognitive Consequences of Technology

Covered transformers, PEFT/LoRA, prompt engineering, Python, and project feedback.