09/05/2026 updated
100 % available
Data Scientist | Machine Learning Engineer
Sangli, India
Only remote
M.Sc. in Computer Science (In Progress)Application Programming Interfaces (APIs)Google BigQueryPostgreSQLMachine LearningNatural Language ProcessingAzure Machine LearningSQLiteSQL DatabasesGoogle CloudCloud Platform SystemFeature EngineeringData ScienceRandom ForestpandasMatplotlib
Machine Learning & Predictive Modeling
Expertise in building and deploying classification and regression ML models using Scikit-learn, XGBoost, Random Forest, and Logistic Regression, achieving high accuracy metrics such as 89.2% accuracy and ROC-AUC of 0.93 on real-world datasets.
LLM Engineering & Retrieval-Augmented Generation (RAG)
Hands-on experience in applied LLM engineering including Retrieval-Augmented Generation, semantic search pipelines using ChromaDB, Sentence-Transformers embeddings, and integration of the Anthropic API for response generation.
Python-Based ETL Pipeline Development
Design and maintenance of Python-based ETL pipelines using Pandas and NumPy to process large-scale datasets with 1M+ rows, reducing data preparation time by 30% and automating repetitive data extraction and transformation tasks.
Cloud Computing with GCP
Utilization of Google Cloud Platform services including BigQuery, Cloud Storage, Google Colab, and Vertex AI for scalable data storage, batch processing, and model deployment as scheduled prediction jobs.
Natural Language Processing (NLP)
Development of text classification models using NLTK, TF-IDF vectorization, and Logistic Regression to detect sentiment from large product review datasets, achieving up to 87% accuracy with LinearSVC.
Data Visualization & Reporting
Creation of dashboards and reports using Matplotlib and Seaborn to communicate data findings to non-technical stakeholders in a clear and actionable manner.
MLOps & Experiment Tracking
Application of MLflow for experiment tracking, FastAPI for model deployment as lightweight endpoints, and Docker for containerization basics, supporting reproducible and scalable ML workflows.
SQL & Database Management
Proficiency in SQL and experience with relational and cloud databases including MySQL, PostgreSQL, SQLite, and BigQuery for data querying, storage, and management.
Feature Engineering & Model Evaluation
Application of techniques such as One-Hot Encoding, StandardScaler, SMOTE for class imbalance, GridSearchCV for hyperparameter tuning, and comprehensive EDA to improve model performance and reliability.
Expertise in building and deploying classification and regression ML models using Scikit-learn, XGBoost, Random Forest, and Logistic Regression, achieving high accuracy metrics such as 89.2% accuracy and ROC-AUC of 0.93 on real-world datasets.
LLM Engineering & Retrieval-Augmented Generation (RAG)
Hands-on experience in applied LLM engineering including Retrieval-Augmented Generation, semantic search pipelines using ChromaDB, Sentence-Transformers embeddings, and integration of the Anthropic API for response generation.
Python-Based ETL Pipeline Development
Design and maintenance of Python-based ETL pipelines using Pandas and NumPy to process large-scale datasets with 1M+ rows, reducing data preparation time by 30% and automating repetitive data extraction and transformation tasks.
Cloud Computing with GCP
Utilization of Google Cloud Platform services including BigQuery, Cloud Storage, Google Colab, and Vertex AI for scalable data storage, batch processing, and model deployment as scheduled prediction jobs.
Natural Language Processing (NLP)
Development of text classification models using NLTK, TF-IDF vectorization, and Logistic Regression to detect sentiment from large product review datasets, achieving up to 87% accuracy with LinearSVC.
Data Visualization & Reporting
Creation of dashboards and reports using Matplotlib and Seaborn to communicate data findings to non-technical stakeholders in a clear and actionable manner.
MLOps & Experiment Tracking
Application of MLflow for experiment tracking, FastAPI for model deployment as lightweight endpoints, and Docker for containerization basics, supporting reproducible and scalable ML workflows.
SQL & Database Management
Proficiency in SQL and experience with relational and cloud databases including MySQL, PostgreSQL, SQLite, and BigQuery for data querying, storage, and management.
Feature Engineering & Model Evaluation
Application of techniques such as One-Hot Encoding, StandardScaler, SMOTE for class imbalance, GridSearchCV for hyperparameter tuning, and comprehensive EDA to improve model performance and reliability.
Experience
Professional experience0 - 5 years
Freelancer since2024
Languages
EnglishFluent
Project history
Designed and maintained Python-based ETL pipelines using Pandas and NumPy to process large-scale datasets (1M+ rows), cutting data preparation time by 30%. Built and deployed classification and regression ML models (Random Forest, XGBoost, Logistic Regression) for predictive analytics, improving operational efficiency by ~15%. Leveraged GCP (BigQuery, Cloud Storage) for scalable data storage, batch processing, and model deployment. Automated repetitive data extraction and transformation tasks using Python and Bash, reducing manual effort by 30%. Created dashboards and reports using Matplotlib and Seaborn. Collaborated with cross-functional teams in an Agile/Scrum environment.
Built a Retrieval-Augmented Generation chatbot using Python, Streamlit, React, ChromaDB, Sentence-Transformers, and Anthropic API. Implemented a semantic search pipeline using ChromaDB and all-MiniLM-L6-v2 sentence embeddings. Integrated the Anthropic API for response generation and designed a React frontend with source-provenance indicators.
Built an end-to-end ML pipeline to predict customer churn on a telecom dataset with 70,000+ records, achieving 89.2% accuracy (Random Forest) and ROC-AUC of 0.93. Applied One-Hot Encoding, StandardScaler, and SMOTE for class imbalance; GridSearchCV tuning improved F1-score from 0.81 to 0.87. Deployed as a batch job on GCP and tracked experiments with MLflow.