# Joshua Tree Karpel

[josh.karpel@gmail.com](mailto:josh.karpel@gmail.com) | [jtk.dev](https://www.jtk.dev/) | [github.com/JoshKarpel](https://github.com/JoshKarpel) | [linkedin.com/in/joshkarpel](https://www.linkedin.com/in/joshkarpel/)

Also available as [Web](https://www.jtk.dev/resume) or [PDF](https://www.jtk.dev/resume.pdf).

## Skills

- [Product-minded](https://blog.pragmaticengineer.com/the-product-minded-engineer/) technical leadership of engineering teams
- Platform, service, and developer tooling engineering, from laptop to production
- Software architecture, from libraries to distributed systems
- Understanding existing code, then refactoring/extracting/migrating/replacing it
- Explaining systems to executives, product managers, and engineers alike
- AI/ML infrastructure, with observability and CI/CD
- Performance and cost optimization, without trading one for the other
- Python primarily, plus Rust and TypeScript in personal projects

## Work Experience

### [Workday](https://www.workday.com/) (November 2020 – Present)

#### Principal Machine Learning Engineer (November 2023 – Present)

- Served as tech lead of our [Ray](https://www.ray.io/)-based model-serving system, which we grew into the company-wide platform for model hosting and external LLM access; designed the sharding system that uses [rendezvous hashing](https://en.wikipedia.org/wiki/Rendezvous_hashing) to spread tens of thousands of models across several physical clusters behind one logical service.
- Reduced our organization's cloud spend by 40% while improving latency and reliability across services within and on top of the AI platform, by optimizing how they use infrastructure rather than just cutting the capacity they run on.
- Helped design and build an [Argo CD](https://argo-cd.readthedocs.io/en/stable/)-based deployment system for the AI platform and the ~150 services on our Kubernetes clusters, cutting pull-request-to-production time from eight hours to three minutes, with [Rego](https://www.openpolicyagent.org/docs/policy-language) policy checks on rendered [Helm](https://helm.sh/) and [Kustomize](https://kustomize.io/) manifests, so bad configuration fails in CI.

#### Senior Machine Learning Engineer (November 2021 – November 2023)

- Led the original design and build of the model-serving system, 50x cheaper than the one it replaced; won a Workday Innovator Award for it in 2023.
- Helped design and build the monorepo that brought our shared inference service framework to dozens of services and hundreds of engineers.
- Migrated a service's model-building and ETL pipelines from our colocated data center to AWS, trading a fixed hardware footprint for elastic capacity; won one of 25 quarterly Outstanding Contributor Awards for the work in Fall 2022.

#### Machine Learning Engineer (November 2020 – November 2021)

- Factored a shareable inference service framework out of an existing service, giving later services a common base to build on.
- Built tooling for defining our alerts and dashboards programmatically, so that observability was reviewed and versioned like the rest of our code.

### [Center for High-Throughput Computing](https://chtc.cs.wisc.edu/) (Summer 2018 – November 2020)

#### Morgridge Postdoctoral Fellow (January 2020 – November 2020)

*Core Computational Technology Group at the [Morgridge Institute for Research](https://morgridge.org/)*

- Worked with researchers to turn their science into automated high-throughput workflows, generalizing one-off solutions into shared tools like [Dask-CHTC](https://github.com/JoshKarpel/dask-chtc).
- Modernized how [HTCondor](https://htcondor.org/) taught and tested itself: rewrote the [Python bindings tutorials](https://htcondor.readthedocs.io/en/latest/apis/python-bindings/tutorials/index.html) for users rather than administrators, and built Ornithology, a [pytest](https://docs.pytest.org/)-based alternative to the existing Perl-based testing framework.

#### Project Assistant (Summer 2018 – Fall 2019)

- Primary developer of [HTMap](https://github.com/htcondor/htmap) and [htcondor.dags](https://htcondor.readthedocs.io/en/latest/apis/python-bindings/api/dags.html) (now part of [HTCondor](https://htcondor.org/) itself), Python packages for describing and running HTCondor workflows.

### [UW-Madison Physics Department](https://www.physics.wisc.edu/) (Fall 2014 – Fall 2019)

#### Graduate Research Assistant (Summer 2015 – Fall 2019)

*[Yavuz Research Group](https://yavuzlab.physics.wisc.edu/group.htm)*

- Modeled [ultrashort intense laser-atom interactions in hydrogen atoms](https://doi.org/10.1364/OL.43.002583) and [nonlinear Raman processes in glass microspheres](https://doi.org/10.1364/OE.27.034154), using the Scientific Python stack and high-throughput computing systems to run millions of simulations.

#### Graduate Teaching Assistant (Fall 2014 – Spring 2018)

- Taught discussion and laboratory sections ranging from electromagnetism and [optics](https://github.com/JoshKarpel/physics325) labs to physics in the arts, and revised the manuals and supplementary materials for the advanced lab courses; won the department's [Joseph R. Dillinger Award for Teaching Excellence](https://www.physics.wisc.edu/instructional/prizes.html) in 2018.

## Selected Talks ([all talks](https://www.jtk.dev/docs))

- [How Workday Achieved 50x Cheaper Model Serving with Ray Serve](https://youtu.be/MfK1FgxCgPA) at [Ray Summit, November 2025](https://www.anyscale.com/ray-summit/2025)
- [Concurrency and Parallelism](https://github.com/JoshKarpel/python-concurrency-and-parallelism) at [MadPy, June 2024](https://madpy.com/meetups/2024/6/13/20240613-concurrency-and-parallelism/)
- [pytest: It's What's For Testing](https://github.com/JoshKarpel/pytest-its-whats-for-testing) at [MadPy, December 2022](https://madpy.com/meetups/2022/12/8/20221208-pytest-its-whats-for-testing/)
- [The Python Data Model](https://github.com/JoshKarpel/python-data-model) at [MadPy, August 2019](https://www.meetup.com/MadPython/events/263151787/)
- [Rust for Pythonistas](https://github.com/JoshKarpel/rust-for-pythonistas) at [MadPy, September 2018](https://www.meetup.com/MadPython/events/252708406/)

## Education

- **Ph.D. in Physics**, University of Wisconsin-Madison (Fall 2014 – Fall 2019)
- **B.A. in Physics and Mathematics**, University of Colorado-Boulder (Fall 2010 – Spring 2014)