Second Look
Tells you whether the cheapest health plan is actually safe for you.
Overall winner, Week 3 · Hacktoberfest 2026
Python · TabPFN · Gemma 4 · Ollama · MEPS data
AI engineer building agents and graph-RAG systems that verify their own output.
Selected work
Tells you whether the cheapest health plan is actually safe for you.
Overall winner, Week 3 · Hacktoberfest 2026
Python · TabPFN · Gemma 4 · Ollama · MEPS data
Finds real ghost reports in 180 years of old American newspapers.
Python · Temporal · MongoDB Atlas · Gemma 4 · Sentry
Answers travel questions only from a verified knowledge graph.
Poster winner · KGC 2026
Neo4j / Cypher · LangChain / LangGraph · Llama 3 · Snowflake Cortex · Python · Streamlit
Makes AI triage of crisis messages reliable in every language.
Best Paper Award · AI4S 2026
Python · Conformal prediction · mBERT · XLM-R · Hugging Face
Catches counting mistakes in knitting patterns, size by size.
TypeScript · Gemma 4 · Qwen3.5-4B LoRA · Ollama
Open source
95.9K stars
8 merged
One of the most widely used engines for running large AI models on servers. I fixed 8 bugs, mostly in how long prompts are trimmed and how uploaded images and videos are checked before the model sees them.
13.6K stars
11 merged
Hugging Face's toolkit for building voice assistants from open models. I fixed how it detects which language someone is speaking, and kept private conversation transcripts out of the server logs.
1.1K stars
8 merged
A research library for looking inside AI models while they run. I fixed bugs, added support for Python 3.14, and made its automated tests cover every Python version it supports.
8.9K stars
19 merged
Open-source AI coworkers for teams. My changes make them safer and easier to audit: they refuse tools a team never added, answer only from documents the person asking may read, and record why a message was not delivered.
41.4K stars
2 merged
Runs very large AI models on small graphics cards. I made it pick the best hardware on the machine instead of assuming an NVIDIA card, which closed three open bug reports.
165.6K stars
18 agents · 8 fixes
One of GitHub's most-starred collections of ready-made AI agents. I wrote 18 of its specialist agents, from Statistician to FinOps Engineer, and fixed 8 bugs in its installer. The maintainer merged most of my agents in combined batches that credit me.
Experience
May 2026 - Present
Open-Source Contributor
Sep 2024 - May 2025
Northeastern University
Graduate Research Assistant
Jan 2025 - Apr 2025
Northeastern University
Teaching Assistant
Jan 2024 - May 2024
Foruppo
Software Engineering Fellow
Feb 2023 - Jul 2023
AppsTek Corp
Research Intern
Writing
HackerNoon
OpenAI's agent escaped containment and hit Hugging Face. The fix isn't smarter models. It's the identity layer the Agentic AI Foundation was built to ship.
HackerNoon
MCP became the standard way to wire tools into AI in 2026. GitHub token leaks, remote-code-execution bugs and supply-chain attacks show the risks that came with it.
DEV
It all started with a sticker. Two years ago, I saw an MLH sticker on a friend's laptop 💻, looked up what it meant, and happened to find Hacktoberfest 2024 running at the same time.
DEV
Why I built this. I've always wondered about ghost stories. American horror movies like The Conjuring say they're based on true events, and they felt real to me, so I wanted to see the real ones for myself.
Recognition
Toolkit