profile picture

Myungjun (MJ) Son

Research Assistant

Education

Ph.D. in Computer Science

The Pennsylvania State University, USA
2019 - 2025 (expected)

Master in Computer Science

Kookmin University, South Korea
2017 - 2019

Bachelor in Computer Science

Kookmin University, South Korea
2010 - 2017

Interests

  • Cloud Computing
  • Serverless Computing
  • Data Analytics

About Theme

Career Profile

Hello! I am a research professional with over 7 years of expertise in computer science, specifically focused on resource management in cloud environments. Currently, I am pursuing a Ph.D. degree in the same field while continuing to expand my knowledge and skills in this area.

CV Google Scholar

Recent News

  • [02/2024] - Accepted a Research Associate Internship at Hewlett Packard Enterprise
  • [07/2023] - Presented the paper at IEEE CLOUD 2023
  • [06/2023] - Started summer internship at Takeda Pharmaceutical

Work Experience

R&D Summer Intern

May 2023 - Aug 2023
Takeda Pharmaceutical, Boston, Massachusetts, USA

Worked in Digital Platforms team and reduced manual efforts through optimizing and automating data pipeline, leveraging AWS services.

  • Enhanced overall system performance, leading to 25% reduction of AWS cost.

Research Assistant

Aug 2019 - Present
Storage Laboratory, The Pennsylvania State University

Topic: efficiency of cloud and distributed systems. (Advisor: Dr. Mahmut Kandemir)

Cloud Assistant

Feb 2018 - Feb 2018
Samsung Electronics, Gyeonggi-do, South Korea

Assisted professor with instructing Cloud Computing course to 40 Samsung developers.

  • Course material includes AWS, Kubernetes, Hive, MongoDB, and Hadoop

Research Assistant

May 2016 - Aug 2019
Kookmin Bigdata Laboratory, Seoul

Topic: Cost-efficient data analytics platform on cloud. (Advisor: Dr. Kyungyong Lee)

Projects

MicroBlend - Automated cloud service selection for microservice-based applications - Developed automated resource blending approach for microservice applications. (9% reduction in SLO violations and 11% cost decrease)
Splice - Combining IaaS with FaaS (ppt) - Designed compiler-driven automatic blended service framework. (32% reduction in cost)
ABC2 - Autonomic Big Data Cloud Computing research project (ppt) - Analyzed Machine Learning kernel (Matrix Multiplication) on cloud environments. (MatMul performance model on Spark with 50% reduction in accuracy error)
DeepSpotCloud - Cost-efficient Deep Learning platform with cloud computing services (pdf) - Used EC2 GPU spot instances to build a cost-efficient deep learning framework. (task migration scheduling policy with 13% more cost gain)

Publications

  • MicroBlend - An Automated Service-Blending Framework for Microservice-Based Cloud Applications
    • Myungjun Son, Shruti Mohanty, Jashwant Raj Gunasekaran, Mahmut Kandemir
    2023 IEEE 16th International Conference on Cloud Computing (CLOUD) (Acceptance Rate - 21%)
  • Splice - An Automated Framework for Cost- and Performance-Aware Blending of Cloud Services
    • Myungjun Son, Shruti Mohanty, Jashwant Raj Gunasekaran, Aman Jain, Mahmut Kandemir, George Kesidis, Bhuvan Urgaonkar
    The 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID 2022) (Acceptance Rate - 24%)
  • Modeling Distributed Matrix Multiplication Performance on a Scale-out Cloud Environment for Data Mining Jobs
    • Jeongchul Kim, Myungjun Son, Kyungyong Lee
    IEEE Transactions on Cloud Computing 2019
  • Distributed Matrix Multiplication Performance Estimator for Machine Learning Jobs in Cloud Computing
    • Myungjun Son and Kyungyong Lee
    2018 IEEE 11th International Conference on Cloud Computing (CLOUD)
  • DeepSpotCloud - Leveraging Cross-Region GPU Spot Instances for Deep Learning
    • Kyungyong Lee and Myungjun Son
    2017 IEEE 10th International Conference on Cloud Computing (CLOUD) (Acceptance Rate - 19%)

    Skills & Proficiency

    Python & Git & R

    AWS, Spark, Compiler

    Microsiervces, Prometheus, eBPF