Journey
The full story.
I'm a Computer Science student at UC Irvine specialising in Intelligent Systems, with a minor in Innovation and Entrepreneurship. Most of what I build sits where machine learning meets a product someone actually has to use.
That's taken me through four internships — credit risk modelling at Scienaptic AI, healthcare document pipelines at Shift Technology, agent infrastructure at Emergence AI, and now data and automation work at CliftonLarsonAllen. The common thread is turning messy, unstructured input into something a system can act on with confidence.
Outside of work I ship my own things, mostly to answer questions I couldn't find good answers to: whether a recruiting platform can level the playing field, whether a prediction engine can be honest about its own accuracy, whether a receipt can track its own deadlines.
Right now — updated July 2026
Working on
- Interning at CliftonLarsonAllen on the digital team, building machine learning and data science tooling.
- Actively building this site — currently the shader background and the recruiter-mode document system.
- MarketEdge — extending the calibration scoring so the engine's own accuracy is measurable over a longer window, not just per-event.
- Getting ReturnTrack from a shipped web app to an app store release.
Learning
- Data pipeline orchestration in earnest — retries, backfills, and what it takes for a scheduled job to fail loudly instead of silently.
- Practical evaluation for LLM-backed features: how to tell whether an extraction step actually got better or just changed.
The full timeline
How I got here
- ProjectJuly 2026
ReturnTrack
Never miss a return window again
Receipt-tracking app using Claude's vision API to extract line items and compute return and warranty deadlines against a self-researched policy database covering 70+ policies across 50 retailers.
- WorkJune 2026 — Present
Data and Automation Intern
CliftonLarsonAllen
Building approval workflows, prompt-versioning tooling, and connectors for an internal AI platform that turns client meeting transcripts into structured automation opportunities.
- ProjectJune 2026 — Present
MarketEdge
In progress
A prediction-market divergence engine — surfaces pricing gaps across markets for the same underlying event, and grades its own calibration over time.
- ProjectMarch 2026 — Present
Scout
Full-stack multi-sport recruiting platform
AI resume generation, coach outreach, and vector-based college matching, plus a browser-based highlight compiler built on FFmpeg.wasm.
- ProjectJanuary 2026
Sprout
Daily learning tracker
A calm, minimal daily-learning tracker — log one thing you learned each day, graded by the Anthropic API.
- WorkJuly 2025 — Sep 2025
Machine Learning Intern
Emergence AI
Built and deployed a standalone compliance MCP server to Emergence's CRAFT platform, decoupling the agent from platform infrastructure and standardizing MCP development.
- WorkJuly 2024 — Sep 2024
Data Science Intern
Shift Technology
Structured medical codes out of healthcare PDFs and refined LangChain pipelines for CPT↔ICD-10 relevance mapping, strengthening LLM evaluation datasets.
- WorkJune 2023 — July 2023
Data Science Intern
Scienaptic AI
Engineered economic and demographic features for credit risk models across 3000+ counties, improving underwriting accuracy and interpretability.
- EducationExpected June 2027
B.S. Computer Science (Intelligent Systems)
UC Irvine — Minor: Innovation & Entrepreneurship
Coursework across machine learning and AI, computer vision, information retrieval, algorithms, and system design.
Beyond the work
Leadership & involvement
Kappa Sigma Fraternity
Jan 2024 — Jan 2025VP of Finance
I served as VP of Finance for Kappa Sigma Fraternity from January 2024 to January 2025, managing a $50,000+ budget on behalf of more than 50 members. I prepared financial models and reports for chapter leadership, which meant translating what the chapter could actually afford into decisions the rest of the executive board could act on.
One of the initiatives I'm proudest of was a philanthropy campaign for Military Heroes, where I helped raise $7,000. Alongside that, I planned chapter events end-to-end — negotiating venue and vendor contracts, which taught me a lot about managing budgets against real-world constraints rather than just a spreadsheet.
Gram Oorja
2022 — 2024Community service — rural sustainable energy nonprofit
I grew up in India, and given the country's demographics I participated in a great deal of community service and charity work. From 2022 to 2024, I worked with a nonprofit called Gram Oorja, which focuses on bringing sustainable energy solutions to rural communities.
I helped organize and oversee a project that installed a solar microgrid in a village of about 200 people, providing running water and electricity to more than 40 households. Being on the ground and working directly with families showed me how transformative the right technology can be, especially in communities that have historically been overlooked.
Toward the end of the project, I even began using early versions of ChatGPT to organize tasks and coordinate communication — and that small introduction showed me how AI could support real-world development work.
Recognition
Awards
- Dean's Honor List, 2024–2026
- Senior Class Valedictorian
- CIF Scholastic Championship
- President's List
Want to talk? eshaan.punalekar@gmail.com