Senior Data Scientist - GenAI & ML

PROFILE SUMMARY:

Sai Likith Deshaboina

USA 216-***-**** ************@*****.*** LinkedIn

Data Scientist with 5+ years of experience designing and deploying data-driven solutions across finance, healthcare, and life-science domains. Proficient in Python, SQL, and PySpark for machine learning, deep learning, and LLM-based NLP applications. Skilled in data wrangling, feature engineering, and EDA on large, complex datasets using Databricks, Apache Spark, and Delta Lake. Hands-on with AWS and Azure for cloud-based analytics and MLOps workflows using MLflow, Docker, and Kubernetes. Experienced in creating interactive dashboards with Tableau and Power BI, and implementing Responsible AI governance to ensure transparency, fairness, and model reliability. TECHNICAL SKILLS:

• Programming & Analytics: Python, SQL, R (working knowledge), SAS, Java, Statistics, Probability, Time-Series Analysis, Feature Engineering

• Machine Learning & AI: Regression / Classification, Ensemble Models (XGBoost, LightGBM), Clustering, Forecasting, NLP, Model Evaluation, Deep Learning (TensorFlow, PyTorch, Keras), Generative AI (LLMs, LangChain, vector databases Pinecone / FAISS)

• Big Data & Platforms: Databricks (Delta Lake, MLflow, Workflows, Unity Catalog), Apache Spark, PySpark, Snowflake, Azure Data Lake

• Cloud & Deployment: AWS (S3, EC2, SageMaker, Lambda, Redshift), Azure ML, Docker, GitHub Actions, CI/CD Pipelines

• Data Engineering: ETL Workflows, Airflow, SQL / PostgreSQL, MySQL, MongoDB, Neo4j (basic exposure), Data Validation & Monitoring

• Visualization & BI: Tableau, Power BI, Plotly, Matplotlib, Seaborn, Streamlit (basic)

• Methodologies & Practices: Agile / Scrum, Model Lifecycle Management, Testing & Documentation, Secure Coding Standards, Cross-Functional Collaboration, Responsible AI Governance WORK EXPERIENCE:

First Horizon Bank Jan 2025 - Present

Sr. Data Scientist Birmingham, Alabama, USA

• Developed and deployed advanced Quantitative and Generative AI models using Python, PySpark, and scikit-learn on Databricks (Delta Lake, Unity Catalog, MLflow) to analyze investment portfolios and forecast market trends.

• Leveraged Deep Learning frameworks such as TensorFlow, Keras, and PyTorch to enhance financial time-series forecasting and market-signal prediction accuracy.

• Designed scalable Big Data pipelines using Apache Spark, Airflow, and Kafka for real-time ingestion and transformation of large-scale market and transactional data.

• Implemented ARIMA and LSTM models for asset price forecasting and client investment behavior prediction, improving trend prediction accuracy by 20%.

• Built LLM- and NLP-driven financial-intelligence tools using LangChain and vector databases (FAISS, Pinecone) to summarize earnings calls and market insights for investment teams.

• Created interactive dashboards and data visualizations in Tableau, Power BI, and Databricks SQL, empowering portfolio managers with real-time investment insights.

• Deployed production-grade MLOps pipelines using MLflow, Docker, and Kubernetes, ensuring scalable, monitored, and version-controlled ML deployments.

• Mentored junior scientists, led code reviews, and established Responsible AI governance frameworks integrating data-quality alerts, drift signals, and cost metrics for proactive model oversight. UAB Medicine Jan 2024 - Dec 2024

Data Scientist Birmingham, Alabama, USA

• Built and deployed predictive models using Python (XGBoost, TensorFlow) to forecast patient admissions and detect claim anomalies, reducing manual workload by 30%.

• Applied NLP techniques with Transformers and spaCy to extract clinical insights from unstructured data, improving risk stratification accuracy by 22%.

• Designed ETL pipelines in Airflow and Snowflake to integrate EHR and claims data for model training and reporting.

• Implemented classification and clustering algorithms to segment patients and optimize provider allocation, boosting efficiency.

• Developed interactive Tableau dashboards to visualize readmission rates and provider efficiency for clinical leadership.

• Deployed models to AWS SageMaker with CI/CD pipelines, ensuring reliability and automated retraining in production.

• Partnered with clinicians and operations teams in Agile sprints to interpret model results and co-design interventions.

• Led cross-functional workshops to drive adoption of AI insights in operational decision-making. Razorpay Jan 2022 - Jan 2023

Data Scientist Bangalore, India

• Built credit-risk and customer-segmentation models using Python and XGBoost, improving default-prediction accuracy by 15%.

• Conducted EDA and feature engineering on financial data using PySpark and Hive to ensure consistency across data sources.

• Automated data ingestion workflows using Airflow and SQL, cutting manual processing time by 40%.

• Designed KPI dashboards in Power BI to track portfolio risk and underwriting performance for BFSI clients.

• Migrated legacy SAS models to Azure ML and TensorFlow, reducing processing time and cloud costs by 20%.

• Partnered with client stakeholders to translate analytical outputs into actionable insights for business and regulatory reporting.

BT Group Sep 2019 - Dec 2021

Data Analyst Bangalore, India

• Collected, cleaned, and validated sales and production data using SQL and Excel to support demand-forecasting initiatives.

• Built interactive dashboards in Power BI to monitor sales performance, inventory trends, and production efficiency.

• Prepared datasets for ARIMA-based demand models, improving forecast accuracy and inventory management by 12%.

• Partnered with manufacturing and quality teams to analyze batch yield and defect rates, reducing process deviations by 10%.

• Automated recurring reports using SQL scripts, increasing reporting efficiency and reducing manual errors.

• Ensured compliance with 21 CFR Part 11 and GDPR standards through secure data documentation and audits. EDUCATION:

University of the Cumberlands — Kentucky, USA Jan 2023 - Dec 2024 Master’s, Information Systems and Security

• GPA: CGPA: (3.8/4.0)

• Coursework: Artificial Intelligence, Machine Learning, NLP, Cloud Computing, Big Data, Data Mining, Advanced Python, Business Intelligence, SQL, Tableau, Python, Algorithms

Contact this candidate