Keston Crandall
Founding ML Backend Engineer at Robyn 🪺
Washington, District of Columbia, United States
Summary
👤
Senior🎓
Top SchoolKeston Crandall is a Founding ML Backend Engineer with 11 years of experience building scalable, revenue-critical AI and server-side systems from pre-seed to production. He architected a full-stack, multi-cloud infrastructure as a solo backend engineer that supported a $5.5M seed raise and real-time sub-second audio pipelines combining transcription, LLMs, and TTS. His background spans dynamic pricing, recommendation systems, OCR/NLP automation, and emotion-detection models that fuse voice, calendar, and HealthKit context to drive personalized experiences. Keston is pragmatic about MLOps—designing automated deployment pipelines, observability, and ACID-compliant billing integrations that keep systems reliable at scale. An avid data engineer and educator, he contributes to open-source data mining tooling (including pyspark-enabled target encoding) and has taught Python, data mining, and analytics at GWU. He blends founder-level product judgment with deep hands-on expertise across cloud, serverless, databases, and ML infrastructure.
11 years of coding experience
8 years of employment as a software developer
Master of Science in Business Analytics (M.S.B.A.) Data Science, Master of Science in Business Analytics (M.S.B.A.) Data Science at The George Washington UniversityBachelor of Business Administration (B.B.A.) Management Information Systems General, Bachelor of Business Administration (B.B.A.) Management Information Systems General at The George Washington University School of BusinessGeneral Education Degree -, General Education Degree - at Sewickley Academy
English
Stackoverflow
119reputation
17kreached
6answers
5questions
Github Skills (16)
data-mining10
machine-learning10
pyspark10
spark10
h2o10
python10
data-science9
r9
pandas8
aws-lambda6
initialization6
xamarin6
xamarin-android6
android6
faunadb6
Programming languages (8)
Github contributions (5)
jphall663/GWU_data_mining
Jun 2017 - Feb 2018
Materials for GWU DNSC 6279 and DNSC 6290.
Role in this project:
Data Scientist
Data ScientistContributions:10 commits, 12 PRs in 8 months
Contributions summary:Keston primarily focused on enhancing the existing data mining and machine learning code base within the repository. Their contributions included fixing bugs in the target encoding function, ensuring it correctly handles values present in test sets but not in training sets. They also made the target encoder pyspark enabled, and added code for preprocessing with spark. This involved refactoring and enhancing the codebase for compatibility with different data frame types and processing frameworks, ultimately supporting more robust data analysis pipelines.
pythonh2oimage-recognitiondata-sciencesas
kcrandall/faunadb-csharp
Mar 2020 - Jul 2020
C# driver for FaunaDB
Contributions:22 pushes in 3 months
faunadbdatabase-accesscsharpdatabasetarantool
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.