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

Data Scientist and AI Engineer with 7+ years of experience architecting and deploying machine learning, NLP, fraud/risk modeling, and retrieval/agentic LLM solutions across healthcare, finance, retail, media, telecom, and e-commerce. Proven delivery of production-grade ML systems including real-time fraud detection, clinical risk modeling and forecasting, RAG applications with LangChain/LangGraph, and end-to-end MLOps using AWS, Spark, Kafka, MLflow, Docker, Kubernetes, and CI/CD—focusing on measurable outcomes, compliance, monitoring, and reliable deployment.…Data Scientist and AI Engineer with 7+ years of experience architecting and deploying machine learning, NLP, fraud/risk modeling, and retrieval/agentic LLM solutions across healthcare, finance, retail, media, telecom, and e-commerce. Proven delivery of production-grade ML systems including real-time fraud detection, clinical risk modeling and forecasting, RAG applications with LangChain/LangGraph, and end-to-end MLOps using AWS, Spark, Kafka, MLflow, Docker, Kubernetes, and CI/CD—focusing on measurable outcomes, compliance, monitoring, and reliable deployment.

Yashwanth Challagali

Data Scientist, AI Engineer, Data Engineer, +2





Data Scientist and AI Engineer with 7+ years of experience architecting and deploying machine learning, NLP, fraud/risk modeling, and retrieval/agentic LLM solutions across healthcare, finance, retail, media, telecom, and e-commerce. Proven delivery of production-grade ML systems including real-time fraud detection, clinical risk modeling and forecasting, RAG applications with LangChain/LangGraph, and end-to-end MLOps using AWS, Spark, Kafka, MLflow, Docker, Kubernetes, and CI/CD—focusing on measurable outcomes, compliance, monitoring, and reliable deployment.…Data Scientist and AI Engineer with 7+ years of experience architecting and deploying machine learning, NLP, fraud/risk modeling, and retrieval/agentic LLM solutions across healthcare, finance, retail, media, telecom, and e-commerce. Proven delivery of production-grade ML systems including real-time fraud detection, clinical risk modeling and forecasting, RAG applications with LangChain/LangGraph, and end-to-end MLOps using AWS, Spark, Kafka, MLflow, Docker, Kubernetes, and CI/CD—focusing on measurable outcomes, compliance, monitoring, and reliable deployment.

Available to hire

Data Scientist and AI Engineer with 7+ years of experience architecting and deploying machine learning, NLP, fraud/risk modeling, and retrieval/agentic LLM solutions across healthcare, finance, retail, media, telecom, and e-commerce.

Proven delivery of production-grade ML systems including real-time fraud detection, clinical risk modeling and forecasting, RAG applications with LangChain/LangGraph, and end-to-end MLOps using AWS, Spark, Kafka, MLflow, Docker, Kubernetes, and CI/CD—focusing on measurable outcomes, compliance, monitoring, and reliable deployment.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

Data Scientist at HCA HealthCare

July 1, 2025 - Present

Architected HIPAA-compliant ETL workflows using AWS Glue, PySpark, and Airflow to process EHR, claims, and wearable data via HL7/FHIR for interoperability across 5+ downstream clinical systems. Built patient readmission risk models (Logistic Regression, Random Forest, XGBoost, LightGBM) improving care management outcomes by ~15%. Developed RAG-based clinical knowledge retrieval (LangChain, FAISS/Pinecone, AWS Bedrock) increasing evidence-grounding relevance by ~20%. Implemented forecasting models (ARIMA/SARIMA/Prophet/LSTM) improving hospital capacity planning accuracy by ~12%. Designed NLP pipelines (BERT/spaCy/NLTK) for diagnosis/medication/lab extraction to automate ICD-10/CPT/LOINC coding, reducing manual effort by ~25%. Built real-time clinical alerting (Kafka, Spark Streaming) reducing care-team response time by ~30%. Implemented PHI de-identification with NER to maintain zero PHI exposure incidents across compliance audits, and used SHAP/LIME for healthcare explainability requir

Data Scientist at Capital One

September 1, 2022 - June 30, 2025

Developed and deployed fraud detection models (Logistic Regression, Random Forest, XGBoost, LightGBM) reducing false positives by ~18% while improving detection accuracy. Built real-time credit risk assessment pipelines integrating transaction data, credit bureau reports, and income attributes for dynamic risk scoring. Engineered churn prediction using behavioral analytics, product usage patterns, and sentiment to enable targeted retention. Estimated loan default risk using PD/LGD/EAD frameworks and applied time-series methods (ARIMA/SARIMA/Prophet/LSTM) for interest rate and payment delinquency modeling. Implemented anomaly detection using Isolation Forest and Autoencoders for AML compliance. Segmented customers with clustering (K-Means/DBSCAN/Hierarchical) for personalized marketing. Built financial monitoring dashboards in Tableau/Power BI. Implemented an agentic RAG-based chatbot (LangChain, LlamaIndex, LangGraph, AWS Bedrock, n8n) reducing analyst investigation time by 60–70%. D

Data Scientist at Macy's

June 1, 2019 - September 30, 2022

Designed and deployed data pipelines to ingest, clean, and transform e-commerce transactional and customer interaction data into a Databricks environment. Automated ETL using AWS Glue and built feature engineering/data enrichment for improved data usability. Developed and validated ML and deep learning models (XGBoost, LightGBM, TensorFlow) for demand forecasting and inventory optimization. Built recommendation systems (collaborative filtering, content-based, and deep learning) for personalized product suggestions. Implemented NLP pipelines with NLTK, spaCy, and BERT for sentiment analysis and keyword extraction from reviews. Created interactive dashboards using Power BI, Tableau, and MicroStrategy for sales trends and inventory health. Scheduled daily pipeline runs via Airflow and Cron; set up real-time alerting integrations with Slack/email for demand shifts and stockouts. Used Kafka for streaming customer interaction events to support near-real-time recommendation updates, and impro

Data Scientist at Macy’s

June 1, 2019 - September 30, 2022

Architected and deployed data pipelines ingesting, cleaning, and transforming e-commerce transactional and customer interaction data into a Databricks environment. Automated ETL with AWS Glue and feature engineering/enrichment. Developed demand forecasting and inventory optimization models including XGBoost/LightGBM and deep learning in TensorFlow. Built recommendation systems (collaborative filtering, content-based, deep learning) for personalized product suggestions. Implemented NLP pipelines (NLTK, spaCy, BERT) for product review sentiment analysis and keyword extraction. Designed interactive dashboards in Power BI/Tableau/MicroStrategy to track sales trends, customer behavior, and inventory health. Automated pipeline executions using Airflow and cron. Partnered with data engineering to optimize SQL and improve ETL efficiency for large-scale datasets. Built scalable NLP workflows with AWS Glue/Airflow improving processing speed and model accuracy. Applied A/B testing, regression, an