Kevin Kho
Building at KnitKnot
Los Angeles, California, United States
Summary
🤩
Rockstar🎓
Top SchoolKevin Kho is an AI-native engineer and founder with 8 years of experience building production ML systems, currently launching KnitKnot after leading AI engineering at Drata. He blends MLOps and backend expertise—contributing to widely used open-source projects like Fugue and the popular DataTalksClub MLOps Zoomcamp—where he added core data-cleaning and orchestration features and integrated MLflow and XGBoost pipelines. Kevin’s background spans consulting for finance and time-series teams, hands-on generative AI work, and community-facing roles at Prefect, giving him a rare mix of product, ops, and open-source stewardship. Based in Los Angeles and trained as a civil engineer at UIUC, he often approaches ML problems with systems-thinking and a practical emphasis on deployment and reliability.
8 years of coding experience
9 years of employment as a software developer
BS/MS Civil Engineering, BS/MS Civil Engineering at University of Illinois Urbana-Champaign
Stackoverflow
687reputation
56kreached
46answers
0questions
Github Skills (24)
continuous-deployment10
xgboost10
prefect10
python10
data-engineering10
pandas10
workflow-engine10
mlflow10
ml-deployment10
mlops10
sql10
orchestration10
dataframe9
distributed-computing9
dataframes9
Programming languages (6)
Github contributions (5)
fugue-project/fugue
Oct 2020 - Jan 2023
A unified interface for distributed computing. Fugue executes SQL, Python, Pandas, and Polars code on Spark, Dask and Ray without any rewrites.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:3 releases, 155 reviews, 138 commits in 2 years 3 months
Contributions summary:Kevin contributed to the Fugue project by implementing and improving core functionalities related to data processing and workflow management. Their work includes adding support for `dropna` and `fillna` operations, crucial for data cleaning and transformation. They also enhanced the library by accepting a list of tuples in presort expressions, contributing to improved flexibility in data organization. Additionally, they worked on the interface, adding the SQL part of `fillna`.
data-practitionerspythondaskfuguedata-science
DataTalksClub/mlops-zoomcamp
May 2022 - Jun 2022
Free MLOps course from DataTalks.Club
Role in this project:MLOps Engineer
MLOps EngineerContributions:17 commits, 5 PRs, 21 pushes in 29 days
Contributions summary:Kevin's contributions center around orchestrating and deploying a machine learning model. They implemented and refined a Prefect-based orchestration pipeline, incorporating features like task definitions and scheduling. They focused on integrating mlflow for experiment tracking and model logging, and also incorporated model training using XGBoost. The user demonstrated an understanding of model deployment and operational aspects of the MLOps lifecycle.
data-sciencemodel-deploymentmachine-learningmlopsmodel-monitoring
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.