Panagiotis Garefalakis
Software Engineer at Amazon Web Services (AWS)
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolPanagiotis Garefalakis is a software engineer with 11 years of experience specializing in large-scale distributed systems, databases, query processing, and resource management, currently building next-generation Open Data Analytics Engines at AWS. He holds a PhD in Distributed Systems from Imperial College London and has a strong track record shipping performance-sensitive features in production at Confluent, Cloudera, and AWS. An active Apache contributor and PMC member for ORC with commit rights in Hive, his open-source work includes deep fixes to ORC schema evolution, predicate pushdown, and LLAP scheduling that improve query latency and correctness. He designed and delivered cross-cloud user code infrastructure for Flink UDFs and led runtime-level enhancements for failure enrichment and aggregation semantics. Based in San Francisco, he combines rigorous academic research on heterogeneous cluster resource management with pragmatic engineering that measurably speeds analytics workloads. Colleagues rely on him for both low-level storage/format expertise and end-to-end query runtime optimizations.
11 years of coding experience
14 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Distributed Systems, Doctor of Philosophy (Ph.D.) Distributed Systems at Imperial College LondonMaster of Science (MSc) Parallel and Distributed Systems, Master of Science (MSc) Parallel and Distributed Systems at University of Crete
English, Greek, German
Github Skills (21)
apache-flink10
testing10
big-data10
java10
javas10
sql10
apache-hive10
orc10
stream-processing10
schema-changes10
hadoop9
data-structure9
cpp9
data-structures9
apache-kafka8
Programming languages (7)
Github contributions (5)
apache/orc
Nov 2020 - Dec 2021
Apache ORC - the smallest, fastest columnar storage for Hadoop workloads
Role in this project:
Back-end Developer
Back-end DeveloperContributions:153 reviews, 29 commits, 105 PRs in 1 year
Contributions summary:Panagiotis primarily contributed to the Apache ORC project by addressing schema evolution issues and improving predicate pushdown performance, which involved modifying core components of the ORC file format. They enhanced the handling of character and varchar types, ensuring correct conversions during schema evolution. The user also fixed bugs related to date and timestamp handling in predicate evaluation, which indicates a deep understanding of the ORC internals and data type implementations. Their work includes adding test cases and modifying existing code.
orccppworkloadscolumnar-storagefastest
apache/flink
Aug 2015 - Aug 2024
Apache Flink
Role in this project:Backend Developer
Backend DeveloperContributions:64 reviews, 19 PRs, 100 comments in 9 years 1 month
Contributions summary:Panagiotis primarily contributed to the Apache Flink project by introducing and modifying failure enrichment and labeling functionalities. Their work involved creating interfaces, utility classes, and integrating these features within the runtime environment, specifically focusing on enhancing how failures are handled and reported during job restarts. The commits demonstrate modifications to existing test classes to validate the newly added failure labeling mechanisms and support for exception history. Furthermore, the user refactored code to integrate failure labels within the REST API.
pythonflinkconnectorsqlapache
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.