Stuti Dumre
Data Scientist
Build, train, deploy, and optimize machine learning models - from data preprocessing and feature engineering to production deployment and continuous monitoring
GET IN TOUCH
Build, train, deploy, and optimize machine learning models - from data preprocessing and feature engineering to production deployment and continuous monitoring
GET IN TOUCH
With expertise in supervised and unsupervised learning, deep learning (CNNs, RNNs, Transformers), and model optimization, I build end-to-end ML pipelines from data preprocessing to production deployment. Experienced with TensorFlow, PyTorch, scikit-learn, and cloud-based model training on AWS.
With expertise in supervised and unsupervised learning, deep learning (CNNs, RNNs, Transformers), and model optimization, I build end-to-end ML pipelines from data preprocessing to production deployment. Experienced with TensorFlow, PyTorch, scikit-learn, and cloud-based model training on AWS.
Proficient in designing and implementing robust ETL pipelines, data transformation workflows, and automated data processing systems. Experience with SQL, Python (Pandas, NumPy), AWS (S3, Lambda), and CI/CD automation for scalable data infrastructure.
I am Stuti, a data scientist and machine learning engineer passionate about building intelligent systems that extract insights from data and solve real-world problems. From the first steps of data collection and exploration through feature engineering, model training, and hyperparameter optimization, all the way to production deployment and monitoring - I can support each step of the process to enable organizations in making evidence-driven decisions.
With 4+ years of experience in machine learning, deep learning, computer vision, and data engineering, I've worked on projects ranging from OCR systems using CNNs to recommendation engines using collaborative filtering, NLP applications with LLMs, and scalable ML pipelines on AWS. I'm proficient in Python, TensorFlow, PyTorch, scikit-learn, and cloud platforms, with a strong foundation in statistical analysis and A/B testing.
I am available for data science consulting, ML engineering projects, and part-time collaborations.
Real-time dashboard using Streamlit and Gemini API with predictive analytics and time series modeling, deployed on AWS EC2.
End-to-end data pipeline with ML models (Random Forest, XGBoost) and TinyLLaMA NLP integration, deployed on AWS with CI/CD automation.
Automated CI/CD pipelines for ML model deployment using AWS services (EC2, S3, Lambda, SageMaker), reducing deployment time by 40%.
Multiple competition entries using ensemble methods, model stacking, and advanced feature engineering. Documented on Medium and GitHub.
TensorFlow, PyTorch, Keras, scikit-learn, OpenAI, LangChain, XGBoost, LightGBM, CNNs, RNNs, Transformers, NLP, Computer Vision
Python, SQL, Pandas, NumPy, ETL Pipelines, Data Warehousing, AWS (EC2, S3, Lambda, SageMaker), Docker, CI/CD
Tableau, Power BI, Matplotlib, Seaborn, Plotly, Statistical Analysis, A/B Testing, Hypothesis Testing, EDA
Email: stuti.dumre@gmail.com
Location: Dayton, OH