Swasti Kakker
Staff Software Engineer at LinkedIn
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolSwasti Kakker is a Staff Software Engineer based in Bengaluru with nine years of experience building and optimizing large-scale distributed systems at LinkedIn. She rose through roles from intern to staff engineer, focusing on back-end performance, reliability, and operational improvements for data-intensive workloads. Her open-source contributions to the notable Dr. Elephant project demonstrate hands-on expertise in Hadoop and Spark performance heuristics, time-skew detection, and pragmatic fixes like aggressive fetcher timeouts and connection timeouts to improve resiliency. Swasti combines deep performance engineering instincts with production-first engineering—adding targeted heuristics for Spark executor GC and configuration thresholds that surface actionable tuning signals. Colleagues describe her as an engineer who pairs low-level systems knowledge with product sensibility, reducing noisy failures while making monitoring more actionable. She holds a B.E. (Hons.) in Computer Science from BITS Pilani and brings a research-minded, metrics-driven approach to system reliability.
9 years of coding experience
8 years of employment as a software developer
BITS Pilani, Birla Institute of Technology and ScienceClass XII, Class XII at Blooming Dales School, Hisar.
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
javas10
spark10
hadoop10
performance-optimization10
java10
scala9
rest-api8
devops7
Programming languages (4)
Github contributions (5)
linkedin/dr-elephant
Jul 2017 - Apr 2018
Dr. Elephant is a job and flow-level performance monitoring and tuning tool for Apache Hadoop and Apache Spark
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:1 release, 28 commits, 27 PRs in 8 months
Contributions summary:Swasti primarily contributed to the Dr. Elephant project by implementing new features and improving the system's reliability. This included adding logic for map reduce time-skew heuristics, fixing file system configurations for Hadoop2, and integrating a second retry queue for fetching Spark metrics. Furthermore, the user added a Spark Executor GC Heuristic and Spark Configuration Threshold Heuristic for performance monitoring and optimization purposes. They also addressed the timeout issues by reducing the timeout of spark fetcher from 60 to 5 seconds and added connection timeout for REST calls.
performance-monitoringelephantapachebig-dataspark
skakker/dr-elephant
Jul 2016 - Apr 2018
Contributions:123 pushes, 30 branches in 1 year 9 months
performance-monitoringapachebig-datasparkperformance
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.