Pradithya Pura
Engineering Manager at Airwallex
Singapore
Summary
🤩
Rockstar🎓
Top SchoolPradithya Pura is an Engineering Manager with 11 years of experience building and scaling cloud-native infrastructure and ML platforms, currently leading Data & AI Infrastructure and Temporal Workflow at Airwallex in Singapore. He drove Gojek’s Kubernetes platform from a handful of services to 1,000+ services in 18 months and played a core role in the company’s large-scale cloud migration that cut costs by over 50%. A hands-on leader with deep backend and MLOps chops, he has contributed to prominent open-source projects such as Feast (feature store) and KServe, focusing on storage/serving, protocol buffers, and model-serving robustness. His background spans embedded systems to distributed ML platforms—evidence of a pragmatic engineer who can move from low-level optimization to platform-wide architecture. He combines technical execution with measurable operational impact and a track record of onboarding and standardizing tooling for enterprise ML teams.
11 years of coding experience
12 years of employment as a software developer
Bachelor of Engineering, Electrical Engineering, Bachelor of Engineering, Electrical Engineering at Institut Teknologi BandungMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at Georgia Institute of TechnologyMaster of Science (MS), Systems Design and Management, Master of Science (MS), Systems Design and Management at National University of Singapore
Github Skills (14)
kubernetes10
xgboost10
machine-learning10
feature-store10
mlops10
go10
python10
redis10
kubernetes-pods10
protocol-buffers10
data-engineering9
tensorflow9
big-data8
istio8
Programming languages (10)
Github contributions (5)
kserve/kserve
Oct 2019 - Mar 2022
Standardized Serverless ML Inference Platform on Kubernetes
Role in this project:
MLOps Engineer
MLOps EngineerContributions:11 reviews, 12 commits, 8 PRs in 2 years 5 months
Contributions summary:Pradithya contributed to the kserve/kserve project by implementing and modifying features related to model serving and deployment. They exposed the `nthread` parameter in the XGBoostSpec, allowing for configurable CPU threading, and they modified the code to correctly convert list input to a numpy array before creating a DMatrix for XGBoost models. They also made modifications related to ingress configuration. Furthermore, they addressed an issue related to content type headers, ensuring proper JSON formatting.
xgboostsklearnserverlessclient-goknative
feast-dev/feast
Dec 2018 - Oct 2019
The Open Source Feature Store for Machine Learning
Role in this project:Back-end Developer
Back-end DeveloperContributions:2 releases, 1 review, 50 commits in 10 months
Contributions summary:Pradithya primarily contributed to the development of core functionalities within the Feast feature store. Their work involved defining and implementing protocol buffer definitions for various services, including core and UI services. The user also added feature serving services and made changes to facilitate data retrieval from Redis, indicating a focus on the storage and serving aspects of the feature store. This suggests a strong involvement in building the backend infrastructure and services for Feast.
pythondata-qualitydata-sciencemlmachine-learning
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.