About Me

I'm Sia Khorsand, a software engineer studying Cognitive Science + CS at UC San Diego. I'm passionate about building intelligent systems that solve real problems.

Right now I'm shipping Chalky, a fitness app that lets people log workouts and journal naturally and get personalized coaching. I was a founding engineer at UniWise, where I wore multiple hats across product, infrastructure, and feature work on an AI tool that helped technicians move 50x faster on contraindication checks.

I'm wired to solve problems across different contexts and constraints. Whether that's collaborating with stakeholders, evaluating whether solutions work, or debugging across unfamiliar systems, I move with resourcefulness and a bias toward clarity. I care deeply about getting the right answer, not just a fast one.

My Philosophy

I work across the full stack. Whether it's shipping features, optimizing infrastructure, designing UX, building data pipelines, or architecting AI systems, I'm equally comfortable moving between them. What matters is solving the right problem, not staying in one lane. That flexibility means I can collaborate effectively with different teams and understand trade-offs from multiple angles.

I build things that make sense. I start by understanding what actually matters to users and stakeholders, then make deliberate decisions about what to optimize for. That clarity carries through to clean APIs, interfaces that don't waste mental energy, and architectures that are reasonable to maintain. Code written this way is easier to debug, extend, and hand off.

I know how to dig into problems. When I hit something unfamiliar or messy, I ask the right questions, debug methodically, and figure out what's actually going on. I work well with other people on teams, talk through trade-offs openly, and make sure we're solving the real problem, not just the first one we see.

I learn from real feedback. I'm rigorous about testing and evaluation, but I'm not dogmatic. The best insights come from teammates, users, and data. I stay curious, adjust based on what I'm learning, and get better at my craft continuously.

Projects

Technical Skills & Toolkit

ML & AI

Supervised & Unsupervised Learning
Reinforcement Learning & Optimization (PPO, genetic algorithms)
Transformer Models & LLM Fine-Tuning (PEFT/LoRA)
Prompt Engineering & LLM Orchestration
Model Evaluation & Deployment
Vector Search & RAG
LLM Security: Prompt Injection, Data Leakage, Guardrails
OCR / PDF Pipelines

Software Development

APIs: FastAPI (REST), WebSockets (real-time)
Auth & Identity: Clerk, JWT, Sessions
Supabase: Postgres, Auth, Edge Functions
Databases: PostgreSQL, MongoDB (Beanie)
Testing: pytest, Type Hints
API Design for Scale: Rate Limits, Idempotency, Audit Logs

Cognitive Science & Product

User-Centered HCI
Conversation Design
User Research & Usability Testing
PRDs, MVP Scoping, Roadmapping
Stakeholder Communication (Eng ↔ Product)
Experimentation Mindset: A/B Tests, Metrics, Funnels
Writing: Clear Specs, Decision Docs, Release Notes
Figma for UX/UI Prototyping
Responsible AI (privacy/compliance-aware product design)

Tools & Data

SQL & Pandas
Supabase RLS & Policy Design
Docker & CI/CD (GitHub Actions)
Observability: Logging, Tracing Basics
Security Basics: Secrets Management, Least Privilege
Cross-Functional Collaboration

Experience

Founder & Software Engineer

Chalky | Dec 2025 – Present

Founder and engineer behind Chalky, an AI-powered fitness app that turns free-form workout notes into structured data, insights, and lightweight coaching. Designed as a product-first system focused on clarity, low friction, and real-world usage.

● Built the end-to-end pipeline to parse unstructured workout logs into validated, structured training data with summaries and weekly insights.
● Designed LLM prompts, schemas, and guardrails to avoid hallucinated metrics and ensure explainable, user-trustable outputs.
● Implemented user authentication, data storage, and policy controls with a focus on privacy, cost efficiency, and scalability.
● Led product decisions around UX, pricing tiers, and feature scope based on real user behavior and feedback.

SwiftUIPythonLLM APIsStructured Outputs & JSON SchemasSupabaseClerkPrompt EngineeringProduct Design

Founding Software Engineer — Backend & AI

UniWise AI | May 2025 – Present | San Diego, CA

Founding engineer on UniWise's core platform, building AI systems for organ-donation workflows. Worked across two flagship products: a real-time call-center triage tool and ContraSight, a document screening and decision-support system.

● Built backend services for live call ingestion, transcription, and structured case generation, enabling faster and more consistent donor screening.
● Developed ContraSight's document pipeline to process EMRs and faxed records, extract key clinical signals, and highlight and annotate surface contraindications for technician review.
● Designed multi-agent AI workflows with human-in-the-loop controls, confidence checks, and audit logs to support safe, reviewable decisions.
● Implemented a retrieval layer grounded in clinical policies and SOPs to improve explanation quality and reduce hallucinations in AI outputs.

PythonFastAPIWebSocketsMongoDBPostgreSQLOCR & PDF ProcessingLLM OrchestrationRAG / GraphRAGAudit Logging & ObservabilityHIPAA-Aligned Design

Course Designer & Instructional Assistant

UC San Diego | Sep 2024 – Jun 2025 | San Diego, CA

Co-designed and supported two Cognitive Science courses, combining co-teaching discussion sections, curriculum work, and student mentorship.

COGS 150: Large Language Models & Cognitive Science
● Facilitated discussions and office hours on LLM mechanics, cognitive implications, and societal impact.
● Graded coding labs/assignments integrating ML fundamentals, AI ethics, and multimodal cognition.

COGS 10: Cognitive Consequences of Technology
● Led discussion sections for 100+ students, connecting cognitive science to real-world technology.
● Mentored students on research design, product design, writing, and presentation.

PythonJupyterGitLLMsProduct DesignUX