Sreeja Bethu

Senior ML Data Scientist

Results-driven Machine Learning Data Scientist with 7+ years of experience architecting end-to-end AI solutions from concept to production. Expert in Generative AI, RAG systems, and delivering significant business value through data-driven insights.

Philadelphia, PA 334-233-0633
PythonPyTorchTensorFlowLangChainRAGLLMsAWSTableauSQL PythonPyTorchTensorFlowLangChainRAGLLMsAWSTableauSQL

Technical Skills

A comprehensive toolkit for end-to-end data science projects

Programming Languages

Multi-language expertise for diverse ML applications

Python
95%
PySpark
88%
SQL
92%
Scala
80%

ML & Deep Learning

Advanced ML frameworks and statistical modeling

TensorFlow/PyTorch
92%
Scikit-learn
95%
Statistical Modeling
90%
Computer Vision
88%

NLP & Generative AI

Cutting-edge NLP and LLM implementations

RAG Systems
95%
LangChain
90%
HuggingFace
88%
Google Gemini SDK
85%

MLOps & Engineering

Production-grade ML pipeline development

Docker/Kubernetes
85%
Apache Airflow
88%
CI/CD Pipelines
82%
FastAPI/Streamlit
90%

Cloud Platforms

Scalable cloud infrastructure and services

AWS (SageMaker, S3)
90%
Databricks
85%
GCP (Vertex AI)
80%
Snowflake
78%

Data Visualization

Business intelligence and data storytelling

Tableau
92%
Power BI
88%
QlikSense
82%
MicroStrategy
78%

About Me

Results-driven Machine Learning Data Scientist with over 7 years of experience architecting end-to-end AI solutions from concept to production.

Professional Experience

Senior Machine Learning Data Scientist

Merck PA | Sep 2023 - Present

Architecting end-to-end ML systems for market share forecasting and prescriber behavior analysis for key drug portfolios.

Machine Learning Analyst

Vitech Systems Asia | May 2021 - July 2022

Led development of AI-powered Intelligent Document Processing system for retirement claims automation. Achieved 95% accuracy in document classification and routing.

ML Data Associate - I

Amazon | Aug 2020 - Apr 2021

Ensured data quality and integrity for large-scale NLP model training datasets and validation processes.

Education

Master of Science in Management Information Systems

Auburn University at Montgomery, USA | 2021 - Dec 2023

Certifications

Microsoft: Generative AI for Business Google Cloud - Introduction to Generative AI Google -Introduction to LLMs Agile Project Manager Certification Cisco: Data Analytics Essentials
25+ML Models Deployed
6+Major Projects
7+Years Experience
60%Process Automation