Karthik Vadla
Software Development Manager at Amazon Web Services (AWS)
Portland, Oregon, United States
Summary
👤
Senior🎓
Top SchoolKarthik Vadla is a seasoned software engineering leader based in Portland with over a decade of experience designing and delivering scalable, cloud-native distributed systems at AWS and Intel. He combines hands-on architecture and coding with people leadership, having grown and mentored teams while driving product roadmaps and zero-downtime migrations for large user bases. His work spans serverless platforms, CI/CD, APIs and data models, and he has operationalized Generative AI (RAG) to boost SME productivity and scaled AWS training platforms to tens of thousands of users. A pragmatic contributor to open-source MLOps and AI tooling, he improved TensorFlow Serving with Intel MKL integration and hardened container build processes for Intel AI reference models—work that directly improved inference performance. Karthik blends deep distributed-systems expertise with a track record of shipping production-grade, secure systems and promoting engineer growth.
10 years of coding experience
12 years of employment as a software developer
Master's Degree Computer Science, Master's Degree Computer Science at Arizona State UniversityBachelor of Technology (B.Tech.) Computer Software Engineering, Bachelor of Technology (B.Tech.) Computer Software Engineering at Gokaraju Rangaraju Institute of Engineering & Technology
English, Hindi, Telugu
Stackoverflow
53reputation
4kreached
1answer
3questions
Github Skills (17)
docker10
python10
bash10
dockers10
cicd10
mlops10
tensorflow10
cpp10
serve10
machine-learning9
bazel9
deep-learning9
html6
windows6
icalendar6
Programming languages (11)
Github contributions (5)
intel/ai-reference-models
Oct 2018 - May 2019
Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Intel® Data Center GPUs
Role in this project:
DevOps Engineer
DevOps EngineerContributions:32 commits, 3 PRs, 4 pushes in 6 months
Contributions summary:Karthik primarily contributed to the repository by modifying scripts and configurations related to the build and deployment process. These changes focused on fixing Python path issues, fixing log locations, and removing hardcoded proxy settings. The user also refactored the docker run subprocess command to remove shell=True. These modifications suggest a focus on improving the containerization and build processes for the project.
optimizationsprocessorstensorflowzoomodel-zoo
tensorflow/serving
Oct 2018 - Feb 2019
A flexible, high-performance serving system for machine learning models
Role in this project:MLOps Engineer
MLOps EngineerContributions:11 commits, 5 PRs, 100 comments in 3 months
Contributions summary:Karthik primarily focused on integrating MKL (Intel Math Kernel Library) support into the TensorFlow Serving system, likely to optimize model inference performance. Their contributions included adding MKL library paths, modifying test data to use MKL, and updating Dockerfiles and test scripts to incorporate and validate MKL-based deployments. The user also made changes to the build process and environment configurations, including adjustments for Ubuntu versions and session parallelism, indicating a strong focus on the operational aspects of the serving system. Furthermore, the user addressed feedback and corrected various syntax errors.
cpppythonservingdeep-learningml
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.