Mar 2024 – May 2025 · 1 yr 2 mos · Hyderabad, Telangana, India · On-site

• Developing large‑scale AI & ML systems for Junk (Dead & Low‑quality) URL detection, improving Bing search quality.
• Fine‑tuned and applied knowledge distillation on a BERT‑based model, achieving 99% precision and 86% AUPRC for Junk URL detection.
• Built a scalable platform blocking 12 billion Junk URLs by integrating unsupervised clustering with a high‑precision classifier.
• Automated URL categorization using LLM (GPT‑4o), reducing human labeling costs by $300K annually.

Aug 2021 – Mar 2024 · 2 yrs 7 mos · Hyderabad, Telangana, India · On-site

• Founding engineer of the Junk Detection team. Secured leadership funding for team expansion to 5 people by building impactful MVP.
• Built real‑time Spark Streaming & Kafka workflows, enabling low‑latency blocking of Junk pages.
• Designed a Big Data graph search algorithm in a query language, detecting over 5 billion Dead pages with 99+% precision.
• Revamped legacy Junk pipelines using Azure tools (Logic Apps, Functions and ARM), significantly reducing on‑call workload.
• Reduced false positives in Junk detection techniques by 75% through in‑depth analysis of user behavior on Edge browser.

Mar 2021 – Aug 2021 · 5 mos · Remote

• TensorFlow Organization at Google:
• Mentored a student on the Community Datasets project in TensorFlow Datasets (TFDS) library.
• The project aimed at exponentially increasing the number of readily available datasets via TDFS with community collaboration.

Jun 2020 – Sep 2020 · 3 mos · Remote

• TensorFlow Organization at Google:
• Contributed to open-source TensorFlow Datasets (TFDS) library.
• Improved backward compatibility and cross‑language support by loading datasets without reading dataset generation code.
• Made TFDS more user friendly by implementing TFDS CLI, folder‑based dataset generation methods, and improving dataset catalog

May 2020 – Jul 2020 · 2 mos · Hyderabad, Telangana, India · Remote

• Edge PDF Reader team at Microsoft:
• Enhanced Scanned PDF accessibility by introducing Optical Character Recognition (OCR) feature in the PDF reader.
• Improved the PDF reader’s capability by enabling users to select and search text in the images of the PDF file.
• Secured a Pre Placement Offer (PPO)

May 2019 – Sep 2019 · 4 mos · Remote

• Worked on open-source HsYAML Library at Haskell Org.
• Developed a open-source HsYAML library for serializing and deserializing YAML documents in Haskell.
• Extended the data model to allow round‑trips while preserving comments, anchors, etc.
• Achieved 99% accuracy on YAML‑Test‑Suite, establishing HsYAML as the best YAML processor.

Jan 2019 – May 2020 · 1 yr 4 mos · IIT Hyderabad

• Teaching Assistant at IIT Hyderabad:
• Principles of Programming Languages course (Jan 2020 - May 2020)
• Artificial Intelligence course (Oct 2019 - Dec 2019)
• Introduction to Data Structure course (Jan 2019 - May 2019)

May 2018 – Jul 2018 · 2 mos · Greater Nagpur Area