Anupam Samanta

About Anupam Samanta

ML/AI Engineer | Search Ads @ GoogleDriving large-scale ML innovation, including Large Language Models, to improve query understanding at Google scale. Delivered launches with multimillion-dollar revenue impact.Previous Experience: • On-Device ML @ Google Nest – Built multimodal ML frameworks powering camera, radar, and audio-based smart device features • Software Engineer Intern @ Evernote • Software Developer (3+ years)@ Samsung & Rubique (FinTech startup)Education & Recognition: • M.S. Computer Science, Stony Brook University (GPA 3.9/4.0) • Graduate coursework: ML, Big Data, Computer Vision, Networks, Databases, Advanced Algorithms, Computational Biology • Awards: Google Research Tech Impact Award; Special mentions from Ads SVPPublications: • QUILL: Query Intent with Large Language Models Using Retrieval Augmentation and Multi-Stage Distillation – arXiv, 2022 • PROMPT: Personalized User Tag Recommendation for Social Media Photos Leveraging Personal and Social Contexts – ISM, 2016Patents: • Method for Training Large Language Models to Perform Query Intent Classification – US Patent App. 18/491,87•••24) • Privacy-Preserving Methods for Personalized Sound Discovery within an Environment – WO Patent WO20••••••22A1 (2022)Technical Skills: Python, C++, TensorFlow, PyTorch, Mediapipe, Distributed Systems, Multimodal ML

Experience

1. Senior Software Engineer

   Google

   Sep 2021 — Present

   I work on the Ads Query Understanding team, where I develop state-of-the-art machine learning models and infrastructure for shopping-related ads on Google Search. As part of the query understanding team, I create ML models that capture query intent, which are used by downstream applications, including retrieval and auctions, as a prefilter to allow only commercial intent. My technical expertise includes C++, Python, and TensorFlow.Key Achievements:Innovative LLM Integration: Introduced Large Language Models (LLM) to search ads query intent, resulting in multiple successful launches that generated $0.X billion in revenue for Google.Leadership: Designed end-to-end projects, from collaborating with research teams and prototyping to establishing distillation pipelines for serving LLMs at Google scale with extremely low latency. Led a team of engineers to explore improvements in the entire pipeline, scoping work for follow-up launches, including introducing continuous distilled models, exploring different architectures in teacher and student model, feature explorations, etc.Recognitions and Awards: Received multiple accolades, including the Research Tech Impact Award and special mentions from the SVP of Ads for one of the most impactful launches of Q2 2023. Presented follow-up tech talks across Google Ads.

Education

• Jawahar Vidya Mandir, Shyamali, Ranchi

  High School , Physics, Chemistry Maths and Computer Science

  2009 — 2010

• Indian Institute of Technology (Indian School of Mines), Dhanbad

  Bachelor’s Degree, Computer Science

  2010 — 2014

• Stony Brook University

  Master of Science - MS, Computer Science

  2017 — 2018

Skills

• Artificial Neural Networks
• Software Development
• Social Computing
• Multimedia
• C
• Computer Vision
• Algorithms
• C++
• Android
• Android Development
• Java