Yoonji Kwon - Postpartum Doula at Doulas by the Bay

Yoonji Kwon

Postpartum Doula at Doulas by the Bay

Berkeley, California, United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Yoonji Kwon is a UC Berkeley bioengineering graduate and community-focused caregiver currently working as a postpartum doula while pursuing goals in medicine. With seven years of experience spanning wet lab research, mentorship program leadership, K-12 education, and farm-based food access work, she combines technical rigor with hands-on community service. She also contributes to open-source AI infrastructure—working on high-profile projects like vLLM and SkyPilot—bringing backend, DevOps, and model-integration experience to scalable ML tooling. Comfortable both behind the scenes managing complex systems and at the bedside providing compassionate care, she excels at translating technical and medical concepts for diverse audiences. Her uncommon blend of bioengineering research, grassroots community engagement, and active involvement in ML infrastructure reflects a practical, service-driven path toward practicing medicine.

7 years of coding experience

3 years of employment as a software developer

Bachelor of Science - BS, Bioengineering, Bachelor of Science - BS, Bioengineering at University of California, Berkeley

English, Korean

Github Skills (27)

pytorch10

docker10

python10

attention-mechanism10

machine-learning10

cloud-infrastructure10

dockers10

transformer-models10

infrastructure10

deep-learning10

gcp9

microsoft-azure9

azure9

cuda9

cli8

Programming languages (6)

C++RustVueHTMLPythonCuda

Github contributions (5)

vllm-project/vllm

Jun 2023 - Apr 2025

A high-throughput and memory-efficient inference and serving engine for LLMs

Role in this project:

Back-end Developer

Contributions:2 releases, 1556 reviews, 1141 PRs in 1 year 9 months

Contributions summary:Yoonji's commits focused on adding core components to the vLLM project, specifically implementing support for the OPT language model. Their work involved defining classes for OPT learned positional embeddings and attention mechanisms, and creating a decoder layer and a complete decoder model compatible with HuggingFace weights. Furthermore, they integrated these components into a causal language model and a block module, demonstrating a focus on model implementation and integration within the project's architecture. The user also added the implementation of the sampling functionalities.

amdcudadeepseekgpthpu

skypilot-org/skypilot

Feb 2022 - Jan 2023

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 14+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

Role in this project:

Backend & DevOps Engineer

Contributions:266 reviews, 259 commits, 39 PRs in 11 months

Contributions summary:Yoonji primarily contributed to the project by fixing bugs, refactoring code, and improving the infrastructure. They addressed issues related to GPU availability checks, docker container management, and Azure image versions. The user also made updates to the CLI, and refactored the DAG optimizer. Furthermore, the user added configuration for W&B setup.

pythonspot-instancesserverlesstpuml-infrastructure

Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.

Request Free Trial