Varun Kiragi

Software developer building full-stack and AI-driven products.

Currently pursuing my M.S. in Computer Science at Georgia Tech. I build reliable, user-focused products across web, mobile, and AI — from iOS apps and ML systems to full-stack tools, with a focus on performance and thoughtful UX.

Email ↗GitHub ↗LinkedIn ↗Resume ↗

Ventures

Solo founder & engineerLive on the US App Store
Nov 2025 — present

Briefing

Live sports scores, bet tracking, and analytics — all in one app. A full-stack sports platform that aggregates live scores, odds, and news across 20+ sports into a single dashboard. Users can track bets with detailed analytics, monitor prop lines in real-time, and pin games for quick access.

  • Built and shipped a full-stack iOS app to the App Store with in-app subscriptions, delivering live scores and AI-powered bet tracking across 20+ sports including NFL, NBA, Tennis, and F1.
  • Engineered a Python/FastAPI backend with real-time API integrations, deployed on Fly.io with rate limiting and connection pooling for production-scale performance.
  • Built a React + TypeScript frontend with Capacitor for iOS, featuring machine learning-driven insights via Gemini 2.5 Flash and a personalized news feed.
ReactTypeScriptTailwind CSSFastAPIPythonSupabaseNetlifyFly.io
App Store ↗Live site ↗View details →

Selected work

Engineering projects across ML, full-stack, and security.

AI Agent · Fintechlablab.ai × Alpaca hackathonLive

Guardrail

An autonomous options-trading agent that structurally cannot reach the broker except through a deterministic risk layer. An LLM produces trading opinions (bullish, bearish, or skip) while a rules engine holds veto power over every order, making risk management structural instead of a matter of trusting the prompt.

  • Separated the agent (opinions only) from a deterministic engine that evaluates six configurable risk gates with no network calls or hallucination exposure.
  • Enforced drawdown halts, symbol allowlists, expiry windows, contract and position limits, and a market-close cutoff before any order reaches the broker.
  • Selected contracts deterministically (always ATM, 7+ days to expiry, one contract, limit orders only) to avoid thin options books.
PythonOpenAIAlpaca APIFastAPISQLiteNetlify
Live ↗GitHub ↗View details →
Machine learningLive

NBA Win-Probability Prediction

End-to-end ML system that predicts NBA game win probabilities, served as an interactive web app with game-by-game backtest report cards.

  • Engineered a leakage-safe pipeline validated with walk-forward testing over 22,800+ held-out games across 19 seasons.
  • Prioritized proper scoring rules (log loss, Brier) and probability calibration over raw accuracy.
  • Best model (logistic regression on Elo + rolling form/rest features) beat a strong Elo baseline while staying well-calibrated.
Pythonscikit-learnXGBoostStreamlit
Live ↗View details →
Full-stack · AI

MailFind

Full-stack NLU search engine that converts conversational email queries into structured, high-precision search.

  • Engineered a full-stack NLU search engine using GPT-5 nano to parse conversational queries into structured JSON, powering a hybrid search combining Supabase filters and pgvector similarity.
  • Architected a Python/FastAPI backend with Google OAuth2, encrypted token storage via Fernet, and an async email indexing pipeline using open-source sentence-transformers for local vector embeddings.
  • Built a Chrome Extension in React and TypeScript injecting a dynamic UI into the Gmail DOM with real-time streaming AI responses.
FastAPIPythonSupabasepgvectorReactTypeScript
GitHub ↗View details →

Experience

Nov 2025 - Present

Founder & Engineer · Briefing

Built and shipped a full-stack iOS app to the App Store with in-app subscriptions, delivering live scores and AI-powered bet tracking across 20+ sports including NFL, NBA, Tennis, and F1.

Sep 2024 - Nov 2024

Software Engineer Intern · The Honey Jar

Led development of a Coin Flip game dApp on Berachain, integrating smart contract interactions with a Next.js and Tailwind CSS frontend.

May 2024 - Aug 2024

Software Engineer Intern · TeamcalAI

Engineered a voice assistant using React Native's Speech Recognition API as sole developer, enabling users to manage schedules via voice commands.

Jun 2023 - Mar 2024

Software Engineer Intern · MyAIChef

Optimized Python web scraping pipelines using pandas and Beautiful Soup.

Education

Jan 2025 - Apr 2027 (Expected)

M.S. in Computer Science (AI specialization)

Georgia Institute of Technology · Atlanta, GA

Sep 2019 - Jun 2023

B.S. in Computer Science

University of California, Davis · Davis, CA

Skills

Languages

TypeScriptJavaScriptPythonCJavaSQLHTMLCSS

Frameworks

ReactNext.jsReact NativeFastAPINode.jsPyTorchscikit-learnpandasNumPyTailwind CSSCapacitor

Tools

DockerKubernetesCI/CDGitLinuxPostgreSQLSupabase

Contact

Currently seeking full-time roles and internships — also open to interesting projects.

varunkiragi@icloud.com
GitHub ↗LinkedIn ↗Resume ↗