Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m Seetha Saryu Vustepalley, a data scientist with around four years of experience building machine learning and statistical models in Python to solve real business problems. My work spans customer analytics, forecasting, and text analytics, and I enjoy turning complex data into clear, decision-ready insights. I also have hands-on experience with Generative AI and LLM/NLP workflows—using techniques like retrieval-augmented generation (RAG), text classification, summarization, and insight extraction. I’m comfortable delivering end-to-end solutions across data pipelines, model governance, dashboards, and compliance-focused environments, and I’m open to relocating from the Denton, Texas area.…I’m Seetha Saryu Vustepalley, a data scientist with around four years of experience building machine learning and statistical models in Python to solve real business problems. My work spans customer analytics, forecasting, and text analytics, and I enjoy turning complex data into clear, decision-ready insights. I also have hands-on experience with Generative AI and LLM/NLP workflows—using techniques like retrieval-augmented generation (RAG), text classification, summarization, and insight extraction. I’m comfortable delivering end-to-end solutions across data pipelines, model governance, dashboards, and compliance-focused environments, and I’m open to relocating from the Denton, Texas area.

Seetha Saryu Vustepalley

Data Scientist, AI Engineer, Data Engineer, +2





I’m Seetha Saryu Vustepalley, a data scientist with around four years of experience building machine learning and statistical models in Python to solve real business problems. My work spans customer analytics, forecasting, and text analytics, and I enjoy turning complex data into clear, decision-ready insights. I also have hands-on experience with Generative AI and LLM/NLP workflows—using techniques like retrieval-augmented generation (RAG), text classification, summarization, and insight extraction. I’m comfortable delivering end-to-end solutions across data pipelines, model governance, dashboards, and compliance-focused environments, and I’m open to relocating from the Denton, Texas area.…I’m Seetha Saryu Vustepalley, a data scientist with around four years of experience building machine learning and statistical models in Python to solve real business problems. My work spans customer analytics, forecasting, and text analytics, and I enjoy turning complex data into clear, decision-ready insights. I also have hands-on experience with Generative AI and LLM/NLP workflows—using techniques like retrieval-augmented generation (RAG), text classification, summarization, and insight extraction. I’m comfortable delivering end-to-end solutions across data pipelines, model governance, dashboards, and compliance-focused environments, and I’m open to relocating from the Denton, Texas area.

Available to hire

I’m Seetha Saryu Vustepalley, a data scientist with around four years of experience building machine learning and statistical models in Python to solve real business problems. My work spans customer analytics, forecasting, and text analytics, and I enjoy turning complex data into clear, decision-ready insights.

I also have hands-on experience with Generative AI and LLM/NLP workflows—using techniques like retrieval-augmented generation (RAG), text classification, summarization, and insight extraction. I’m comfortable delivering end-to-end solutions across data pipelines, model governance, dashboards, and compliance-focused environments, and I’m open to relocating from the Denton, Texas area.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

Data Scientist at JPMorgan Chase & Co.

May 1, 2025 - Present

Developed Python-based credit risk and portfolio analytics models using transactional and customer behavior data to improve risk segmentation accuracy by 17%. Built a Retrieval-Augmented Generation (RAG) solution with LangChain, GPT-4, and PostgreSQL to automate analysis of policy documents and internal risk guidelines, reducing analyst review time by 40% while maintaining audit and compliance traceability. Implemented time-series forecasting (ARIMA, Prophet) to project delinquency and default trends and monthly volumes with 92% forecast accuracy. Processed large-scale financial datasets using PySpark and AWS Redshift to reduce Tableau reporting latency by 35%. Operationalized ML workflows with AWS Lambda and MLOps practices for model governance, version control, cost monitoring, and regulatory compliance (GDPR/CCPA).

Jr. Data Scientist at LTIMindtree

January 1, 2021 - December 1, 2023

Analyzed healthcare datasets from HMIS and EHR workflows using Python, Pandas, and NumPy to identify data quality issues, patient trends, anomalies, and feature relationships, improving model input quality by 30%. Built supervised ML models (Decision Trees, Random Forests, Naive Bayes, SVM, XGBoost) for healthcare prediction/classification using ICD-10 and structured clinical attributes, improving accuracy by 18%. Conducted cohort analysis and hypothesis testing on healthcare utilization, claims, and patient engagement data to identify outcome drivers and support retention improvements of 12%. Created NLP pipelines using NLTK, Keras, and PyTorch for healthcare text classification, sentiment analysis, and summarization of clinical feedback, improving actionable insight coverage by 40%. Developed Power BI and Excel dashboards integrating BigQuery and MongoDB to monitor healthcare KPIs and data quality while aligning analytics workflows with HL7 FHIR and ABDM data standards.