Yashraj Muthyapwar

Data Scientist transforming raw data into actionable insights at the intersection of analytics, machine learning, and business intelligence.

Available for work
United States

👋 About

Profile

I build end-to-end data products

I’m a Data Scientist passionate about turning complex data into intelligent, real-world solutions. I focus on machine learning, analytics, and scalable AI systems. From data discovery and feature engineering to model selection, deployment, and monitoring, I love transforming ambiguity into measurable impact and creating solutions that truly make a difference.

🛠️ Skills

Machine Learning & Deep Learning
Python Python TensorFlow PyTorch PyTorch Scikit-learn Scikit-learn XGBoost XGBoost Keras Keras Hugging Face Hugging Face spaCy spaCy A/B Testing Hyperparameter Tuning Model Evaluation
LLM & Generative AI
RAG Pipelines LangChain LlamaIndex LlamaIndex Prompt Engineering LLM APIs LLM APIs (OpenAI, Anthropic) Ollama Ollama ChromaDB Pydantic Pydantic RAGAS RAGAS LLM Fine-tuning
AWS Cloud & ML Platform
SageMaker Icon-Architecture/32/Arch_Amazon-Bedrock_32 Bedrock Lambda S3 Kendra Icon-Architecture/32/Arch_Amazon-OpenSearch-Service_32 OpenSearch AWS Glue Kinesis CloudFormation CloudWatch API Gateway EC2 Icon-Architecture/32/Arch_Amazon-Elastic-Container-Service_32 ECR/ECS Step Functions EventBridge
Data & Platform Engineering
Pandas NumPy MLflow Phoenix FastAPI Flask Streamlit Streamlit DVC DVC Git GitHub Docker Docker Kubernetes (EKS) SQL PySpark Linux Logo Linux MongoDB

⤷ Experience

2023

Octazen Software Solutions · Data Scientist Intern

At Octazen, customer churn was climbing and no one really knew why. I wasn’t handed a clean dataset or a clear plan, just a problem that needed fixing. I started with a quick logistic regression baseline, moved through Random Forest and XGBoost, and ended up with a model that held its ground 88% accuracy and 0.91 AUC. But models in notebooks don’t change outcomes, so I built a FastAPI microservice with versioned /score and /health endpoints, turning it into something teams could actually use in production.

Meanwhile, I teamed up with data engineering to clean up the backend mess smarter indexes, tighter joins, fewer round trips which cut query latency by 35%. Suddenly, dashboards started updating faster and churn risk wasn’t a mystery anymore. My biggest takeaway? Great models matter, but impact comes from shipping systems that work every single day.

⚙️ Projects

Featured

NotionAtlas AI Semantic Search & RAG for Notion

Turns your Notion workspace into a conversational, context-aware assistant with semantic search, Retrieval-Augmented Generation, and real-time answers.

Featured

HR Analytics Dashboard

Interactive Tableau dashboard that surfaces early-tenure and travel-related attrition drivers; current overall attrition 16.1%.

DATA PIPELINE

Automated Data Pipeline & Interactive Dashboard

End-to-end ETL from API / web scraping / CSV → pandas transforms → SQLite → a sleek Streamlit app. Containerized with Docker and schedulable with Airflow.

AI

PrepWise LinkedIn Interview AI

Turns LinkedIn job posts into live, voice-driven mock interviews with instant AI scoring and natural TTS - right on the job page.

🎓 Education

2024 - Present

Master's of Science in Data Science

University of North Texas, USA   GPA: 4.0/4.0

Focused on Machine Learning, Analytics, and Artificial Intelligence with hands-on projects in data modeling, visualization, and deployment.

Machine Learning Statistics Cloud AI Data Analytics
2019 - 2023

Bachelor's of Technology in Computer Science

Malla Reddy College of Engineering, India   GPA: 3.56/4.0

Gained strong foundations in Algorithms, Data Structures, and Databases with experience in full-stack and software engineering projects.

Data Structures Algorithms DBMS Software Engineering

🏆 Certifications

AWS Certification Badge
2025

AWS Certified ML Engineer Associate

Amazon Web Services

Validates expertise in building, training, tuning, and deploying machine learning models on AWS. Demonstrates proficiency in MLOps, SageMaker, model optimization, and production ML systems.

AWS Certification Screenshot
MongoDB Certification Badge
2025

MongoDB Certified Python Associate

MongoDB University

Demonstrates proficiency in using Python with MongoDB, including PyMongo driver, CRUD operations, aggregation pipelines, indexing, and building Python applications with MongoDB.

📮 Get in touch

Open to roles and collaborations in data science, ML, and analytics. Prefer email first.

🖥️   Portfolio Console

yashraj@portfolio:~$
yashraj@portfolio:~$ Welcome to my portfolio terminal!
yashraj@portfolio:~$ Type 'help' to see available commands
yashraj@portfolio:~$
Portfolio Assistant
Hi! I'm Yashraj's assistant. Ask me about his projects, skills, or experience!