Kivan Polimis
  • Home
  • Technical Articles
  • Blog
  • Vita
  • Teaching
  • Software
  • Projects

On this page

  • Featured Work & Open Source
  • Writing

Kivan Polimis

I’m a Data Scientist and ML Engineer working at the intersection of public policy and scalable machine learning systems.

Currently: Data Scientist at Karna, Chief Data Scientist at Atlas Analytics, and Regional Affiliate at the University of Washington’s Center for the Study of Demography and Ecology (CSDE).

My Philosophy: I operate at the intersection of Public Policy and Machine Learning Engineering. My background in rigorous academic research (Demography/Causal Inference) allows me to ask the right questions, while my engineering experience allows me to build the scalable systems to answer them.

Kivan Polimis


Featured Work & Open Source

  • Generative AI for Healthcare (Private): Architected a privacy-first, multi-agent LLM orchestration framework using RAG to automate clinical documentation, reducing provider administrative load by 40%.
  • Real-Time Sports Analytics (Private): Designed an end-to-end MLOps pipeline on AWS handling live data ingestion to model non-stationary performance metrics for the 2024-2025 NBA season.
  • Scikit-Learn Ecosystem: Contributor to forest-confidence-interval and author of the associated JOSS paper for calculating variance in Random Forest predictions.
  • Large-Scale Optimization: Former Technical Lead for Data Science for Social Good, architecting paratransit routing systems that optimized thousands of daily trips.
  • Financial Transaction NLP: Developed a transformer-based microservice to categorize noisy financial text, utilizing custom loss functions to solve extreme class imbalance.

Writing

Technical Articles → Reproducible analyses, tutorials, and deep dives in Python and R.

Blog → Notes, reviews, and shorter pieces.


Contact: kivan.polimis@gmail.com

Source Code
---
title: "Kivan Polimis"
page-layout: full
title-block-banner: false
---

<div style="display: flex; flex-wrap: wrap; align-items: center; gap: 40px; margin-bottom: 40px;">

<div style="flex: 2; min-width: 300px;">

I'm a Data Scientist and ML Engineer working at the intersection of **public policy** and **scalable machine learning systems**.

Currently: Data Scientist at [Karna](https://karna.com), Chief Data Scientist at [Atlas Analytics](https://www.analyticsbyatlas.com/), and Regional Affiliate at the University of Washington's [Center for the Study of Demography and Ecology (CSDE)](https://csde.washington.edu).

**My Philosophy:** I operate at the intersection of *Public Policy* and *Machine Learning Engineering*. My background in rigorous academic research (Demography/Causal Inference) allows me to ask the right questions, while my engineering experience allows me to build the scalable systems to answer them.

</div>

<div style="flex: 1; text-align: center; min-width: 250px;">
<img src="images/kivan_polimis_headshot.png" alt="Kivan Polimis" style="width: 250px; height: 250px; border-radius: 50%; object-fit: cover; border: 3px solid #eee;">
</div>

</div>

<hr>

### Featured Work & Open Source

- **Generative AI for Healthcare (Private):** Architected a privacy-first, **multi-agent LLM orchestration framework** using RAG to automate clinical documentation, reducing provider administrative load by 40%.
- **Real-Time Sports Analytics (Private):** Designed an **end-to-end MLOps pipeline on AWS** handling live data ingestion to model non-stationary performance metrics for the 2024-2025 NBA season.
- **Scikit-Learn Ecosystem:** Contributor to [forest-confidence-interval](https://github.com/scikit-learn-contrib/forest-confidence-interval) and author of the associated [JOSS paper](https://joss.theoj.org/papers/10.21105/joss.00124) for calculating variance in Random Forest predictions.
- **Large-Scale Optimization:** Former Technical Lead for [Data Science for Social Good](https://github.com/DSSG-paratransit/main_repo), architecting paratransit routing systems that optimized thousands of daily trips.
- **Financial Transaction NLP:** Developed a **transformer-based microservice** to categorize noisy financial text, utilizing custom loss functions to solve extreme class imbalance.

<hr>

### Writing

[**Technical Articles →**](technical.qmd)
Reproducible analyses, tutorials, and deep dives in Python and R.

[**Blog →**](blog.qmd)
Notes, reviews, and shorter pieces.

<hr>

**Contact:** [kivan.polimis@gmail.com](mailto:kivan.polimis@gmail.com)
 

© Kivan Polimis. Built with Quarto.