Satarupa Guha

About Satarupa Guha

I am currently working on cutting-edge AI products in the coding space, at CoreAI, DevDiv. Previously, I have worked on AI quality for Azure OpenAI Service: On-Your-Data which is a Retrieval-Augmented-Generation (RAG) service building on top of OpenAI models.Past experiences- Speech Recognition for Indian languages for products such as Azure Cognitive Services, Bing Voice Search, Cortana, and other 3rd party client products (like phone voice assistant, set-top box etc.)- Search and Relevance for Bing- Interned at Xerox Research Center India in summer 2016 and Flipkart Data Science in 2014 and 2015- Prior to joining Microsoft, I completed MS by Research at Hyderabad, working in the Search & Information Extraction Lab under the guidance of Prof. Vasudeva Varma & Prof. Manish Gupta. Areas of interest: Machine Learning, Large Language Models, Text Generation, Responsible AI, Language Understanding, Sentiment Analysis, Speech Recognition, etc.

Experience

1. Senior Applied Scientist, Core Ai

   Microsoft

   Sep 2022 — Present · Redmond, WA, US

   I’m working on Code Editing/Completions for Github Copilot at Microsoft\'s Developer Division (DevDiv), CoreAI.In my previous stint, I worked on AI quality for Azure OpenAI Service: On-Your-Data which is a Retrieval-Augmented-Generation (RAG) service building on top of OpenAI models, a product that became GA within a year in Jan 2024.Before this, as part of the Azure Language skills team, I worked on leveraging large language models for(a) Multi-lingual models for Opining Mining,(b) Creative content generation solutions usings LLMs targeting a variety of customer scenarios.(c) Contributed towards Responsible AI for the use of LLMs in the new Bing Chat.

Education

• Heritage Institute of Technology, Kolkata

  Bachelor of Technology (BTech), Computer Science and Engineering

  2009 — 2013

• International Institute of Information Technology Hyderabad (IIITH)

  Master's Degree, Computer Science

  2013 — 2016

Skills

• Sentiment Analysis
• Html
• Mysql
• C++
• Information Retrieval
• Matlab
• Data Structures
• Javascript
• Lucene
• C
• Programming
• Python
• C#
• Machine Learning
• Natural Language Processing
• Java
• Twitter Api
• Algorithms
• Sql
• Linux
• Research