resume

gainesville, fl · gpa 3.80 / 4.00

• coursework: data structures & algorithms (C++), computer organization, discrete mathematics

San Diego, California

• Shipped AI-powered event-creation tooling and full-stack features on a 10-engineer team, owning each from spec through production deploy
• Built attendee matchmaking end to end (CSV ingestion and validation, vector-similarity matching, automated email delivery), cutting a manual 2-hour workflow to under 5 minutes
• Designed the Campaign feature’s lead-generation workflow and built its Django de-duplication and scoping logic
• Fixed 5+ production bugs in the campaign and email workflows within 24 hours each, adding edge-case tests to prevent regressions

Remote

• Co-developed a diagnostic framework that separates perception from reasoning failures in audio-language models on Google’s Massive Sound Embedding Benchmark (MSEB)
• Owned the measurement and statistics track on a 4-person team, building an evaluation framework with 8 task adapters, 10 metrics, a blind LLM-as-judge with cost accounting, and 750+ passing tests
• Implemented mixed-effects models, bootstrap CIs, and the Reasoning Robustness Index, and ran a power analysis showing the planned study stayed underpowered even at 800 items per condition

Python, PyTorch, vLLM, LoRA, ALFWorld

• Developing an open-source PyTorch framework for testing AI agents that learn from experience, comparing written memory lessons against LoRA fine-tuning on the model’s own successes
• Running a controlled study on Qwen3-4B across 200 ALFWorld tasks, comparing success and prompt length
• Created a noise-injection test mislabeling 20% of self-grades to measure how grading errors affect learning

TypeScript, Next.js, React Native, FastAPI, LangGraph, Databricks

• Built a web dashboard and iOS app for an AI inspection triage platform backed by a 14-tool LangGraph agent
• Designed a severity-ranked triage queue narrowing 490 Spot robot inspection results to 13 findings
• Wrote 140+ Jest/Vitest tests across web, mobile, and shared code and wired both apps to the FastAPI backend

Python, Swift, FastAPI, PostgreSQL, Redis/Celery, React.js

• Built an iOS 17 application and 60+ endpoint FastAPI backend for wellness protocol tracking, daily logging, progress visualization, and LLM-generated weekly summaries
• Architected production infrastructure with JWT auth, iOS Keychain and Fernet encryption, async SQLAlchemy/PostgreSQL, background jobs, notifications, and Apple Health integrations
• Launched on the App Store and grew to 100+ users logging 1,000+ monthly check-ins, with 5% on premium