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

Data Scientist/GenAI Specialist with 10+ years of experience building and deploying advanced analytics and AI solutions across healthcare, finance, retail, and insurance. Expert in Generative AI, NLP, LLM fine-tuning, and RAG systems using embeddings and vector search. Leads end-to-end ML/GenAI pipelines—from data preparation and model development to validation, deployment, monitoring, and continuous improvement—while applying rigorous statistical testing, explainability (SHAP/LIME), and compliance practices (HIPAA/GDPR) to deliver measurable business and regulatory impact.…Data Scientist/GenAI Specialist with 10+ years of experience building and deploying advanced analytics and AI solutions across healthcare, finance, retail, and insurance. Expert in Generative AI, NLP, LLM fine-tuning, and RAG systems using embeddings and vector search. Leads end-to-end ML/GenAI pipelines—from data preparation and model development to validation, deployment, monitoring, and continuous improvement—while applying rigorous statistical testing, explainability (SHAP/LIME), and compliance practices (HIPAA/GDPR) to deliver measurable business and regulatory impact.

Neha Reddy





Data Scientist/GenAI Specialist with 10+ years of experience building and deploying advanced analytics and AI solutions across healthcare, finance, retail, and insurance. Expert in Generative AI, NLP, LLM fine-tuning, and RAG systems using embeddings and vector search. Leads end-to-end ML/GenAI pipelines—from data preparation and model development to validation, deployment, monitoring, and continuous improvement—while applying rigorous statistical testing, explainability (SHAP/LIME), and compliance practices (HIPAA/GDPR) to deliver measurable business and regulatory impact.…Data Scientist/GenAI Specialist with 10+ years of experience building and deploying advanced analytics and AI solutions across healthcare, finance, retail, and insurance. Expert in Generative AI, NLP, LLM fine-tuning, and RAG systems using embeddings and vector search. Leads end-to-end ML/GenAI pipelines—from data preparation and model development to validation, deployment, monitoring, and continuous improvement—while applying rigorous statistical testing, explainability (SHAP/LIME), and compliance practices (HIPAA/GDPR) to deliver measurable business and regulatory impact.

Available to hire

Data Scientist/GenAI Specialist with 10+ years of experience building and deploying advanced analytics and AI solutions across healthcare, finance, retail, and insurance. Expert in Generative AI, NLP, LLM fine-tuning, and RAG systems using embeddings and vector search.

Leads end-to-end ML/GenAI pipelines—from data preparation and model development to validation, deployment, monitoring, and continuous improvement—while applying rigorous statistical testing, explainability (SHAP/LIME), and compliance practices (HIPAA/GDPR) to deliver measurable business and regulatory impact.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Work Experience

Credit Risk Data Scientist at Credit Karma – California

December 1, 2025 - Present

Designed, validated, and migrated credit risk features and models for short-term lending products (BNPL and installment-style decisioning). Built end-to-end ML pipelines for feature generation, training, scoring, and monitoring using Python, SQL, BigQuery, Airflow, and internal ML infrastructure. Led distributed ML/GenAI pipeline work on multi-terabyte datasets, optimizing compute/memory and scaling feature engineering and scoring to billions of records. Partnered with risk, product, and platform teams to align model thresholds with risk appetite and lending policies. Implemented production monitoring using AUC/KS/Gini plus PSI/CSI for stability and drift, and performed row-level parity validations for safe rollouts. Applied fairness/interpretability practices (feature audits, distribution checks, SHAP) to support FCRA/ECOA governance. Supported production retraining/backfill workflows and built/validated adverse-action logic and risk segmentation driven by model outputs.

Data Scientist / Gen AI Engineer at AAA Insurance – Dallas, Texas

April 1, 2024 - December 1, 2025

Designed and deployed scalable ETL/ELT pipelines with Apache Spark, Airflow, and SQL to support GenAI workflows. Built Retrieval-Augmented Generation (RAG) pipelines using OpenAI embeddings, Pinecone, and LangChain for regulated enterprise retrieval with auditability. Developed real-time streaming systems using Kafka and Spark Streaming for low-latency GenAI use cases (fraud detection and recommendation). Ingested and embedded unstructured content (documents, chat logs, code snippets) for LLM fine-tuning and assistant use cases. Implemented LangChain agents integrated with internal knowledge bases/APIs, and automated GenAI training/evaluation/deployment with MLflow, DVC, and Airflow for reproducible iterations. Partnered with DevOps/compliance teams to launch HIPAA/GDPR-aligned GenAI capabilities, including security controls, logging, access control, and data minimization. Containerized and deployed models using Docker/Kubernetes and Terraform, and built vector search infrastructure an

Data Scientist / Gen AI Engineer at JPMorgan Chase – New York, New York

February 1, 2022 - March 1, 2024

Built EVEE, a GenAI-powered assistant for call center agents to provide contextual, real-time answers. Fine-tuned LLMs using internal documentation and historical customer interactions for domain-specific generation. Implemented RAG pipelines with LangChain, OpenAI APIs, and Pinecone to retrieve and summarize enterprise data. Worked with call center operations, legal, and compliance teams to ensure safe, regulatory-aligned responses and integrated GenAI with CRM systems for live interaction support. Engineered prompts and safety constraints aligned with business/compliance rules, created fallback logic for edge/ambiguous queries, and developed prompt experimentation/batch testing frameworks to improve edge-case coverage by 30%. Built monitoring dashboards and telemetry pipelines for latency/usage/performance and provided secure data handling via RBAC, encryption, and activity logging.

Data Scientist at Home Depot – Atlanta, Georgia

September 1, 2020 - January 1, 2022

Delivered end-to-end ML pipelines for predictive analytics, including ingestion, preprocessing, model training, and deployment for enterprise applications. Performed EDA on large datasets and developed classification/regression models using Random Forest, XGBoost, and neural networks. Built time-series forecasting models (ARIMA, LSTM, Prophet) for demand and inventory optimization. Optimized Spark/Hadoop workflows to reduce query runtimes by 40%. Developed explainable AI using SHAP/LIME and built dashboards in Tableau/Power BI/Plotly. Implemented recommendation systems (collaborative filtering and matrix factorization) and built NLP applications (sentiment, summarization, document classification) using BERT/spaCy/Hugging Face. Automated ETL workflows with Airflow/PySpark/SQL, implemented A/B testing and hypothesis testing frameworks, and deployed models using Docker/Kubernetes and REST APIs. Built monitoring and retraining pipelines with MLflow/DVC/CI-CD for continuous improvement.

Data Scientist at Spencer Health Solutions – Aerial Center Pkwy, Morrisville

July 1, 2018 - August 1, 2020

Evaluated real-time patient interventions (reminders, nudges, telehealth prompts) to improve medication adherence. Collected/cleaned adherence and engagement data from smart dispensers while ensuring HIPAA/ISO compliance. Conducted large-scale EDA to identify adherence patterns and risk factors for trial dropout. Built statistical and ML models (t-tests, chi-square, survival analysis; Random Forest/XGBoost/LSTM) to measure intervention effectiveness and predict adherence likelihood. Developed time-series models (ARIMA/LSTM/Prophet) for adherence trend monitoring and early non-adherence detection. Built dashboards for clinicians and pharma stakeholders and supported real-world evidence (RWE) generation for regulatory submissions. Implemented A/B testing/hypothesis testing and production deployments using Docker/Kubernetes and AWS SageMaker, integrated with clinical workflows.

Python Developer at Solugenix – Hyderabad, India

September 1, 2015 - March 1, 2018

Developed Python-based applications for data processing, automation, and analytics. Wrote optimized scripts for ingestion, transformation, and validation across CSV/JSON/APIs/databases. Built RESTful APIs using Flask/Django for integration between internal systems and external applications. Applied OOP best practices for maintainable/reusable code. Worked with SQL and NoSQL databases (MySQL, MongoDB, Cassandra) and collaborated with data science teams to integrate ML models into production Python applications. Conducted code reviews, debugging, and performance optimization to ensure scalable software delivery.