Sai Kumar Naik Mude
Hi, I'm Sai Kumar Naik Mude, a Gen AI Engineer and Data Scientist with 10 years of experience delivering production-grade AI and data solutions across healthcare, banking, and retail.
About
Hi, I’m Sai Kumar Naik Mude, a Gen AI Engineer and Data Scientist with 10 years of experience delivering production-grade AI and data solutions across healthcare, banking, and retail. I specialize in end-to-end ML systems, spanning data ingestion, feature engineering, modeling, deployment, monitoring, and governance.
I have a strong background in predictive analytics, classical ML, deep learning, and NLP, with hands-on experience building scalable pipelines and deploying models on AWS, Azure, and GCP. I focus on responsible AI, explainability, bias mitigation, and regulatory compliance, while collaborating closely with product and engineering teams to translate requirements into measurable, production-ready outcomes.
- 9 years' experience
- Joined November 2025
Industry experience
- Healthcare
- Financial Services
- Retail
- Professional Services
- Software & Internet
- Other
More experts in Houston, United States
- AI Developers for hire in Houston, United States
- AI Engineers for hire in Houston, United States
- Cloud Developers for hire in Houston, United States
- Data Analysts for hire in Houston, United States
- Data Scientists for hire in Houston, United States
- Full Stack Developers for hire in Houston, United States
- Web Developers for hire in Houston, United States
Work experience· 13 roles
Designed and deployed AI-driven patient risk models, improving early-risk detection and treatment accuracy by 25%. Implemented explainable AI with SHAP and LIME via SageMaker Model Monitor. Built NLP pipelines for document classification and entity extraction. Created LLM-based assistants with Amazon Bedrock and LangChain to summarize clinical reports and patient histories. Built RAG pipelines using LangChain, FAISS, and Amazon OpenSearch for medical literature retrieval. Established real-time claims ingestion and fraud detection pipelines with AWS Kinesis, Lambda, and Glue, reducing manual review time by 35%. Implemented anomaly detection with Isolation Forest and Scikit-learn via AWS Batch, automated retraining with Step Functions and Docker, and deployed population health forecasting models with PyTorch on SageMaker. Set up continuous model monitoring with Evidently AI and CloudWatch to track drift and stability. Ensured HIPAA-compliant data security using AWS IAM and KMS.
Designed and deployed AI-driven patient risk models using Python, TensorFlow, and AWS SageMaker, improving early-risk detection and treatment accuracy by 25%. Enhanced transparency with SHAP and LIME through SageMaker Model Monitor. Built treatment recommendation systems using Keras and TensorFlow to optimize therapy decisions and patient outcomes. Developed NLP pipelines with SpaCy, Hugging Face Transformers, and Amazon Comprehend Medical for document classification and entity extraction. Created LLM-based assistants with Amazon Bedrock and LangChain to summarize clinical reports and patient histories. Built RAG pipelines with LangChain, FAISS, and Amazon OpenSearch for medical literature retrieval. Implemented real-time claims ingestion and fraud detection pipelines with AWS Kinesis, Lambda, and Glue, reducing manual review time by 35%. Automated retraining workflows with AWS Step Functions, Lambda, and Docker, improving model deployment speed. Developed predictive analytics workflow
Designed and deployed credit risk scoring models improving loan approval accuracy and reducing false declines by 20%. Built fraud detection using Isolation Forest, Autoencoders, and PyTorch on Azure Databricks for real-time anomaly detection. Developed LLM-powered NLP pipelines with LangChain, Hugging Face, and Azure Cognitive Services to extract insights from regulatory filings and financial reports. Implemented RAG frameworks leveraging Azure OpenAI and FAISS to automate regulatory summarization and risk insights generation. Built churn prediction models with XGBoost, LightGBM, and Azure Synapse Analytics, increasing retention precision. Developed GNN-based AML models with PyTorch Geometric and Neo4j. Designed ETL workflows with Python, Azure Data Factory and SQL. Automated CI/CD pipelines for ML and GenAI models using Docker, Terraform, and Azure DevOps. Applied SHAP and LIME for bias and fairness and maintained GDPR/Basel II compliance. Created knowledge-graph AML systems integrati
Education
Hire Sai Kumar Naik Mude today
Post a job and invite Sai, or contact them directly. No hidden commission.









