Open to opportunities

sutirtha saha

@sutirthasaha

Message

Data Scientist building scalable NLP and customer analytics solutions.

India

Message

What I'm looking for

I’m looking to build and productize enterprise AI—especially NLP, conversational AI, and customer analytics—working with stakeholders to ship scalable ML solutions, deepen my GenAI/LLM/RAG capability, and grow through impactful research and publishing.

I’m a results-driven Data Scientist with end-to-end experience in ML/NLP pipelines, customer analytics, and predictive modeling across insurance, finance, and retail. I translate complex business problems into scalable AI solutions—blending machine learning with information extraction, natural language generation (NLG), and conversational AI.

Across internships and analytics work, I’ve built reusable model components using Python, SQL, TensorFlow, and Scikit-learn, and delivered stakeholder-ready outputs through dashboards and reports. I’m actively building my Generative AI readiness through prompt engineering and LLM tooling (including RAG concepts), and I’m eager to contribute to AI platform development while continuing to publish research that pushes enterprise NLP forward.

Experience

Work history, roles, and key accomplishments

Data Science Intern

Internship Studio

Feb 2026 - Mar 2026 (1 month)

Analyzed large COVID-19 and financial datasets with end-to-end EDA, cleaning, and preprocessing to surface meaningful trends. Built loan risk segmentation models and interactive dashboards, translating statistical findings into actionable insights for business and marketing stakeholders.

Python Pandas NumPy Data Cleaning Customer Analytics Risk Modeling Matplotlib SeaBorn Statistical Analysis

Data Science Intern

Innovateloop Solutions

Feb 2026 - Mar 2026 (1 month)

Engineered an end-to-end ML pipeline using Logistic Regression, Decision Tree, and Random Forest, including evaluation with accuracy, confusion matrices, and cross-validation. Implemented preprocessing and class-imbalance handling with SMOTE to produce reusable, scalable model components and stakeholder-ready findings.

Python Logistic Regression Decision Trees Random Forest Model Evaluation Cross Validation SMOTE

Claims Relationship Officer

Star Health & Allied Insurance

Jan 2024 - Jan 2025 (1 year)

Analyzed customer interaction data to identify operational bottlenecks supporting retention and quality improvement initiatives. Maintained digital interaction logs in Excel and used SQL for querying and reporting while collaborating with sales and operations teams to streamline workflows.

SQL Excel Data Quality Compliance Reporting Business Analytics