Welcome 🗿

My general vibe:

•AI power user. Zellij, Pi, Helix, Zed, and too many agent windows open at once.
•Into AI infra, full-stack stuff, and making systems robust enough to just work.
•Quite studious and active.

View resume Connect on LinkedIn Read the blog

Lately

Work

Building agent systems, microservices, and full-stack product work at Avathon. Mostly AI infrastructure, retrieval pipelines, and platform engineering.

UT Austin OMSAI

B.S. in CS & Math from UT Austin, now doing the online MS in AI part-time while working full-time. Currently taking Online Learning & Optimization and Deep Learning.

Gym, tennis & cycling

Usually try to be active 6× a week between lifting, tennis lessons, and cycling. Sometimes I go 6/6, other times I'm at 1/6. I play it by ear.

TV & reading

Recently finished Snowfall and Succession — currently watching Shrinking. Book-wise, just read Stoner and How Machines Learn. Always something in rotation.

Work experience

Data Scientist

Avathon · Oct 2025 – Present

⌄

Working across AI infrastructure, internal tools, full-stack systems, and platform decisions — a lot more engineering-heavy than a pure data science role.

Built AI-oriented microservices and agent workflows for internal infrastructure, focusing on making systems useful, reliable, and easier to extend.
Created agent experiences over Avathon's proprietary computational knowledge graph, including retrieval patterns, embeddings-based workflows, and querying interfaces that made the graph significantly more usable.
Worked full-stack on a transport management system, especially around resource-selection configuration flows and the operational logic behind them.
Pitched using DBOS for workflow durability and orchestration, and helped move that idea into practice.
Currently working on more AI infrastructure, including Langfuse integration, while continuing to pick up stronger instincts around microservices, frontend architecture, and day-to-day DevOps realities.

Data Science Intern

IBM · May 2023 – Aug 2023

⌄

Built and deployed a Flask proof of concept integrating Watson Assistant with Db2, helping close a client deal.
Created a 1.5k-line Dash app using watsonx, Discovery, and a custom evaluation API for LLM comparisons.
Owned backend API integration for a React and Flask onboarding MVP on IBM Cloud and OpenShift.

Undergraduate Researcher — Earthquake Modeling

UT Austin · Jan 2024 – May 2024

⌄

Re-engineered a legacy Mathematica SDOF solver into a multithreaded Python pipeline.
Processed 29k+ NGA West2 records and ran 64-vCPU GCP sweeps, cutting runtime from roughly 3 years to about 2 weeks.
Produced interactive Plotly dashboards and a seminar deck for faculty presentation.