Haoran“Tommy” Fang

Software engineering & applied AI.
Turning complex problems into useful systems.

UT Austin
Statistics & Data Science

Explore selected work

Based in Austin, Texas
Available January 2027

Intelligence is only the beginning.
Making it useful is the work.

I build across the stack, from retrieval and model inference to APIs and the interfaces people use. The interesting part is making all of it work together.

Download my resume

Built to answer
real questions.

Revantage · Document intelligence

Hundreds of pages.
A clear answer.

A document-intelligence system that turns 400–800-page loan agreements into 22 source-linked fields. Retrieval, reranking, validation and correction rules make the output traceable, not just plausible.

1–2 minextraction time
90%+answer-key agreement

Built and handed off for secure, non-production Azure deployment. Review time fell from 30–60 minutes to under 5; executives estimated 300+ hours of potential savings.

Document intelligenceSource-linked output
From agreement to evidence.
Input400–800 pages
Structured output22 fields
RetrievalFAISS + reranking
ValidationAnswer-key agreement
Correction layerReusable JSON rules

System overview, not a screenshot of confidential employer data.

Co-developed · Cloudflare Workers / Hono

The right listing.
Not yesterday’s.

A deployed real-estate search and alerting platform with public read APIs, protected writes and an auditable trail of new listings, price changes and status changes.

15 minscheduled evaluations
72 hoursfreshness expiration
Listing FinderSearch → evaluate → alert
New listingRule matched
A new possibility.Matched against a saved search
Price changeTracked
A change worth knowing.Auditable price-change events
Freshness72-hour window
Old data has an expiry.Stale listings are explicitly identified

Illustrative workflow, not live property data.

Embedding Inference Service

A self-hosted FastAPI batch embedding API with CPU/GPU execution, model caching, health checks, telemetry and load tests. Benchmarks document cost–latency tradeoffs against hosted inference.

Repository

ECG Neural Network Classifier

A reproducible PyTorch pipeline over 100K+ ECG recordings: 0.821 test AUROC, 0.791 AUPRC and 0.018 calibration error. Research only; not clinically validated.

Repository

Insurance Intelligence Assistant

A React chatbot over a proprietary insurance API, making operational data accessible to engineering and transactions teams through natural language. Completed a non-production handoff.

Synthetic demo

Intent + LLM Chatbot

Flask inference for a 12-layer TensorFlow Conv1D classifier across 20+ investment intents and 2,000+ labeled examples, with 89% held-out accuracy and an optional LLM response path.

Repository

Ideas meet
the real world.

From enterprise document workflows to inference services and full-stack applications.

Revantage (Blackstone)

AI Engineering Intern

Built and handed off document intelligence and an API-backed insurance assistant for secure, non-production Azure deployment. Python, FastAPI, React, FAISS and PostgreSQL.

Glynac AI

Initial Member of Technical Staff

Built investment-intent inference and LangChain/Qdrant semantic retrieval over 100+ investment documents, returning source-grounded evidence through vector search.

Springer Capital

Data Science Intern

Engineered a workforce-intelligence application with Next.js, TypeScript, Prisma and Azure PostgreSQL to centralize analysis and surface sentiment-derived employee-risk signals.

JPMorgan Chase

Software Engineer Intern

Built a Java/React banking dashboard backed by Cassandra, with editable account workflows and automated interest calculations for internal users.

Good answers
stand up to
hard questions.

Mercor

Evaluate and refine model responses used for personality training, applying structured rubrics across tone, behavioral consistency, instruction adherence, naturalness and conversational quality.

Handshake AI

Design adversarial source-extraction and response-generation tasks. Evaluated 100+ outputs against 10-criterion rubrics to document reasoning, grounding and generation failures.

Evaluation work is under NDA through Mercor and Handshake AI, not direct OpenAI employment. No confidential tasks or model outputs are shared here.

Curiosity, with
follow-through.

I’m studying Statistics and Data Science at UT Austin, with minors in Computer Science and Business. I’m drawn to the space between a model that works and a system people can trust.

The University of Texas at Austin

B.S. Statistics and Data Science
GPA 3.93 · Graduating December 2026

Tools I work with

Python, TypeScript, SQL, Java, C++
PyTorch, TensorFlow, FAISS, Qdrant
FastAPI, React, Next.js, PostgreSQL, Azure
Docker, Terraform, Git and CI/CD

What’s next

Software engineering and applied AI roles starting January 2027.

Let’s make
something useful.

tommyfang2004@gmail.com