Vijay Tadikamalla
Software Engineer III at Google
Hyderabad, Telangana, India
Summary
🤩
Rockstar🎓
Top SchoolVijay Tadikamalla is a Software Engineer III with seven years of experience building large-scale AI, ML, and big data systems, currently improving transcription quality at Google. Previously at Microsoft he was a founding engineer for Junk Detection, architecting real-time Spark/Kafka pipelines and graph search algorithms that blocked billions of low-quality URLs and saved hundreds of thousands in labeling costs by automating workflows with LLMs. He combines hands-on production engineering—deploying Spark Streaming, Azure automation, and knowledge-distilled BERT models—with a strong open-source pedigree as a TFDS contributor and GSoC mentor. Vijay’s work consistently emphasizes precision and operational efficiency (e.g., 99% precision for Junk URL detection and $300K annual labeling savings). Comfortable across research, production, and community projects, he has a track record of turning prototypes into high-impact platforms. Based in Hyderabad, he brings an uncommon mix of applied ML rigor and tooling-focused engineering that accelerates both model quality and system reliability.
7 years of coding experience
5 years of employment as a software developer
Bachelor of Technology - BTech Computer Science, Bachelor of Technology - BTech Computer Science at Indian Institute of Technology Hyderabad
English, Hindi, Telugu, Marathi
Github Skills (1)
testing10
Programming languages (10)
Github contributions (5)
tensorflow/datasets
Jan 2020 - Dec 2020
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:44 reviews, 178 commits, 200 PRs in 11 months
Contributions summary:Vijay primarily focused on cleaning up test cases within the `tensorflow/datasets` repository. Their contributions involved updating dataset versions, cleaning up test files for various image, text, video, and other dataset types, and removing unnecessary parameters related to number of shards. The impact of these changes was improving code quality, and potentially reducing test run times.
datanumpydeep-learningdatasetmachine-learning
vijayphoenix/datasets
Jan 2020 - Aug 2021
A collection of datasets ready to use with TensorFlow
Contributions:4 PRs, 440 pushes, 84 branches in 1 year 7 months
datasetstensorflow
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.