Default profile banner
SB

Sumeet Bisen

@Sumeet100

Machine Learning Engineer at Exponentia.ai

Mumbai

https://linkedin.com/in/sumeet-bisen-34214a20b

Exponentia.aiNational Institute of Technology Karnataka (NITK), Surathkal

Sumeet Bisen is a Data Engineer and Machine Learning Engineer with over three years of experience building scalable data pipelines and production-grade Generative AI systems. He specializes in Databricks, PySpark, and LLM-powered automation. Sumeet has a proven ability to design end-to-end architectures, ranging from OCR-driven data ingestion to Text-to-SQL solutions, effectively transforming complex enterprise data into actionable insights.

Experience

Machine Learning Engineer

Exponentia.ai

Aug 2024 - PresentMumbai, Maharashtra, India

Built real-time speech analytics pipeline on Azure Functions App using Azure Whisper + GPT-4o for automated transcription and sentiment analysis. Developed LLM-powered email classification system and automated region-wise KPI reporting. Delivered Neo4j knowledge graph POC. Built enterprise RAG chatbot using AWS Textract and designed Text-to-SQL solutions for natural language querying of financial datasets. Implemented LLM guardrails and real-time Kafka + Databricks ingestion pipelines.

Business Analyst (Data & ML Engineering)

Genpact

Jul 2022 - Jan 2024

Designed SAP to ADLS ETL pipelines using Azure Data Factory. Migrated forecasting workflows from Pandas to PySpark, achieving 5x performance improvement. Built LLM-powered Q&A proof-of-concept using Weaviate vector database.

Education

National Institute of Technology Karnataka (NITK), Surathkal

B.Tech

Computer Science & Engineering

Jan 2018 - Jan 2022

Licenses & Certifications

Databricks Certified Generative AI Engineer Associate

Databricks

Issued: Jan 2024• No expiration

Skills

Generative AI
GPT-4o
Azure OpenAI
AWS Bedrock
LangChain
RAG
NLP
Prompt Engineering
AWS Textract
OCR
PySpark
Databricks
Spark Structured Streaming
Apache Kafka
Azure Data Factory
ETL/ELT
ADLS
AWS S3
ChromaDB
Weaviate
Databricks Vector Search
Neo4j
Python
SQL
Java
C++
FastAPI
Django
REST APIs
Docker
Git
CI/CD
MLOps