Sameer Gupta

Data Scientist

Rajasthan, India0 mo experience
AI EnabledAI ML Practitioner

Key Highlights

  • Expert in building ML training and inference pipelines.
  • Proven track record in developing generative AI applications.
  • Strong analytical skills with a focus on data-driven insights.
Stackforce AI infers this person is a Data Scientist specializing in Generative AI and Machine Learning solutions for SaaS applications.

Contact

Skills

Core Skills

Generative AiMachine LearningNatural Language Processing

Other Skills

AlgorithmsAzure AI SearchAzure App ServiceAzure Data Lake StorageAzure DatabricksAzure Devops PipelinesAzure Document IntelligenceAzure Machine LearningAzure OpenAIC++Data ScienceData StructuresData VisualizationDatabase Management System (DBMS)Databricks Model Registry

Experience

Celebal technologies

Associate Data Scientist

Jan 2022Present · 4 yrs 2 mos · Gurugram, Haryana, India · Hybrid

  • Project: Document QnA Chatbot using GenAI
  • Built the real-time Chatbot system using the RAG pipeline.
  • Used Azure Document Intelligence to extract text, images and tables from the document and OpenAI Ada2 Embedding model to generate vector embeddings.
  • Used Azure AI Search to store vector embeddings and performed vector search.
  • Utilized OpenAI GPT4o model to chat with text and images in the document.
  • Performed regression testing and auto-eval testing and automated the testing using Azure Devops Pipelines.
  • Project: SWOT Report Generator using GenAI
  • Extracted text from the document using Azure Document Intelligence in the markdown format.
  • Used OpenAI Ada2 Embedding model to generate text embedding and Azure AI Search as vector database and performed vector search using from the database.
  • Built the RAG pipeline using OpenAI GPT3.5 model to generate SWOT Report
  • Project: NAICS Classification using DistilBERT
  • Performed data gathering and data validation by scraping through linkedin and rocketreach website.
  • Performed data cleaning and preprocessing of the gathered company data using spacy.
  • Used DistilBERT model to classify companies based on the NAICS codes and achieved the f1-score above 0.80 for each category.
  • Deployed the model on Azure App Service using FastAPI and Docker
FastAPIAzure Document IntelligenceOpenAI Ada2Azure AI SearchOpenAI GPT4oAzure Devops Pipelines+4

Whitehat jr

Data Analyst

Aug 2021Dec 2021 · 4 mos · Remote

Education

The LNM Institute of Information Technology

Bachelor of Technology — Computer Science

Jan 2018Jan 2022

Stackforce found 100+ more professionals with Generative Ai & Machine Learning

Explore similar profiles based on matching skills and experience