Senior Data Scientist NLP, MLOps & Time Series

Tilak Kumar Bonala

Data Scientist

**********.*@************.*** +1-330-***-**** LinkedIn

SUMMARY

• Data Scientist with 4+ years of experience delivering end-to-end solutions in data extraction, feature engineering, statistical modeling, and machine learning to drive actionable insights and measurable business impact.

• Expertise in building scalable data pipelines and automating ETL workflows using Python, SQL, Apache Airflow, and dbt, ensuring data accuracy, consistency, and seamless integration across diverse systems.

• Proficient in developing and deploying NLP models using transformer-based architectures (BERT, GPT, T5) via Hugging Face and Vertex AI, enabling scalable applications in sentiment analysis and text classification.

• Skilled in MLOps practices, including model containerization with Docker, tracking with MLflow, and deployment on AWS SageMaker and GCP Vertex AI for secure, production-grade machine learning workflows. SKILLS

Language and Tools: Python, R, SQL, Vertex AI, Generative AI IDEs: Visual Studio Code, Anaconda

ML Algorithm: Linear Regression, Logistic Regression, Decision Trees, Random Forests, Naive Bayes, K Means Deep Learning: ANN, CNN, RNN, Hugging Face Transformers (BERT, GPT), LLMs Packages: NumPy, Matplotlib, spaCy, Scikit-learn, Seaborn, TensorFlow, PyTorch, NLTK, OpenCV, MLFlow Cloud Technology: AWS (EC2, S3 Bucket, Amazon Redshift, Lambda, DynamoDB) Visualization Tools: Tableau, Power BI

Database: SQL Server, MySQL, MongoDB, PostgreSQL

Operating System: Windows, Linux, MacOS

PROFESSIONAL EXPERIENCE

Ohio Department of Health 01/2023–present Ohio, Columbus Data Scientist

• Deployed deep learning-based time series models (LSTMs, Prophet), significantly improving epidemic trend forecasting accuracy by 30% and enhancing statewide healthcare emergency planning systems.

• Built unsupervised anomaly detection frameworks (Isolation Forest, DBSCAN), increasing early error detection in patient health records by 25% and improving overall data quality and reliability.

• Automated and optimized ETL pipelines using Apache Airflow and Pandas, reducing manual data processing by 40% and streamlining ingestion, validation, and regulatory compliance reporting.

• Analyzed vaccination outreach campaigns with Bayesian inference techniques, uncovering valuable insights that boosted immunization rates by 15% in underserved rural communities.

• Engineered real-time geospatial dashboards with Power BI, visualizing disease spread patterns and enabling faster, data-driven decisions by emergency response teams.

• Collaborated with cross-functional teams to define analytics objectives and deliver insights, leading to a 20% improvement in recommendation systems and 15% increase in retention.

• Applied statistical techniques (regression, t-tests, A/B testing) to evaluate product changes, resulting in a 12% uplift in engagement and 10% higher conversion rates. Hexaware Technologies 06/2020 – 08/2022 Mumbai, India Data Scientist

• Built and Executed supervised and unsupervised machine learning models using Scikit-learn, PyTorch, and XGBoost, improving prediction accuracy and reducing decision turnaround time.

• Designed and optimized ETL pipelines using SQL, Pandas, and Apache Airflow, automating workflows and cutting manual data processing by 40%, while increasing data accuracy by 25%.

• Developed and fine-tuned NLP models using BERT and T5, automating document classification and chatbot responses, boosting query resolution speed by 30%.

• Conducted EDA and statistical analysis with Python and R, identifying actionable insights for campaign optimization and strategic planning.

• Created real-time dashboards in Tableau, reducing reporting time and enhancing KPI visibility.

• Configured containerized models with Docker and Kubernetes, enabling faster model rollouts and achieving high availability in hybrid cloud environments.

• Implemented time series forecasting with Prophet, ARIMA, and LSTM, increasing forecast accuracy and reducing overstocking in supply chain operations.

EDUCATION

Master of Science in Business Analytics 12/2023

Kent State University Kent, Ohio

CERTIFICATIONS

Aws Machine learning Associate

Contact this candidate