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

I am an AI & GenAI Engineer with 5+ years of hands-on experience delivering end-to-end machine learning and generative AI solutions across healthcare and insurance. I specialize in Python-based modeling, TensorFlow, XGBoost, and ETL orchestration, and I have built production-grade pipelines on AWS and Azure using Glue, PySpark, LangChain, and RAG architectures. In every project, I focus on measurable impact, from reducing latency to improving retrieval accuracy, while maintaining robust security and governance. I enjoy collaborating with cross-functional teams to deploy scalable LLM endpoints, automate workflows with n8n, and monitor performance with Prometheus and Application Insights. I continuously refine prompts, integrate feedback loops, and translate complex requirements into reliable, cost-efficient MLOps solutions that empower claims teams and clinicians.…I am an AI & GenAI Engineer with 5+ years of hands-on experience delivering end-to-end machine learning and generative AI solutions across healthcare and insurance. I specialize in Python-based modeling, TensorFlow, XGBoost, and ETL orchestration, and I have built production-grade pipelines on AWS and Azure using Glue, PySpark, LangChain, and RAG architectures. In every project, I focus on measurable impact, from reducing latency to improving retrieval accuracy, while maintaining robust security and governance. I enjoy collaborating with cross-functional teams to deploy scalable LLM endpoints, automate workflows with n8n, and monitor performance with Prometheus and Application Insights. I continuously refine prompts, integrate feedback loops, and translate complex requirements into reliable, cost-efficient MLOps solutions that empower claims teams and clinicians.

Saideep Reddy Thaduru

AI Engineer, Data Scientist, Full Stack Developer, +3





I am an AI & GenAI Engineer with 5+ years of hands-on experience delivering end-to-end machine learning and generative AI solutions across healthcare and insurance. I specialize in Python-based modeling, TensorFlow, XGBoost, and ETL orchestration, and I have built production-grade pipelines on AWS and Azure using Glue, PySpark, LangChain, and RAG architectures. In every project, I focus on measurable impact, from reducing latency to improving retrieval accuracy, while maintaining robust security and governance. I enjoy collaborating with cross-functional teams to deploy scalable LLM endpoints, automate workflows with n8n, and monitor performance with Prometheus and Application Insights. I continuously refine prompts, integrate feedback loops, and translate complex requirements into reliable, cost-efficient MLOps solutions that empower claims teams and clinicians.…I am an AI & GenAI Engineer with 5+ years of hands-on experience delivering end-to-end machine learning and generative AI solutions across healthcare and insurance. I specialize in Python-based modeling, TensorFlow, XGBoost, and ETL orchestration, and I have built production-grade pipelines on AWS and Azure using Glue, PySpark, LangChain, and RAG architectures. In every project, I focus on measurable impact, from reducing latency to improving retrieval accuracy, while maintaining robust security and governance. I enjoy collaborating with cross-functional teams to deploy scalable LLM endpoints, automate workflows with n8n, and monitor performance with Prometheus and Application Insights. I continuously refine prompts, integrate feedback loops, and translate complex requirements into reliable, cost-efficient MLOps solutions that empower claims teams and clinicians.

Available to hire

I am an AI & GenAI Engineer with 5+ years of hands-on experience delivering end-to-end machine learning and generative AI solutions across healthcare and insurance. I specialize in Python-based modeling, TensorFlow, XGBoost, and ETL orchestration, and I have built production-grade pipelines on AWS and Azure using Glue, PySpark, LangChain, and RAG architectures. In every project, I focus on measurable impact, from reducing latency to improving retrieval accuracy, while maintaining robust security and governance.

I enjoy collaborating with cross-functional teams to deploy scalable LLM endpoints, automate workflows with n8n, and monitor performance with Prometheus and Application Insights. I continuously refine prompts, integrate feedback loops, and translate complex requirements into reliable, cost-efficient MLOps solutions that empower claims teams and clinicians.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

GenAI Engineer at Humana

February 1, 2025 - Present

Built a document-intelligence pipeline using LangChain, RAG, and OpenAI GPT-4 to extract key terms and context from insurance policies and claims; reduced lookup latency by 92% and improved retrieval precision by 18%. Deployed LLM endpoints through Azure OpenAI and orchestrated workflows in n8n, enabling automated document routing and response generation across 5 internal claims systems. Developed modular RAG components with FAISS and Azure Cognitive Search, improving semantic recall for multi-page claim PDFs and cutting manual triage effort by 70%. Integrated feedback loops using LangChain agents and Azure Functions to retrain retrieval prompts based on reviewer corrections, steadily increasing factual accuracy across 20K+ monthly queries. Monitored inference performance with Prometheus + Azure Application Insights, automating latency alerts and optimizing token usage reducing compute cost per query by 27%.

AIML Engineer at Centene Corporation

October 1, 2023 - January 1, 2025

Designed ML workflows in Python and scikit-learn to predict patient readmission risk using claims and EHR data; improved recall on high-risk cohorts by 17% after feature refinement. Rebuilt ETL pipelines on AWS Glue and S3 to process 120 M+ claim records weekly, reducing model training latency from 3 hrs to under 1 hr through optimized partitioning. Containerized a RAG-based clinical insights assistant with LangChain and OpenAI GPT-4, enabling care teams to query patient summaries and guidelines; cut document search time by 80%. Parsed models via SageMaker endpoints and integrated monitoring with CloudWatch to track drift and inference cost, maintaining more than 97% uptime across environments. HIPAA constraints validated output ensuring PHI security while reducing manual review hours by 40%.

Machine Learning Engineer at Neon IT Systems

June 1, 2019 - November 1, 2021

Spearheaded supervised models in Python (scikit-learn, XGBoost) to detect anomalous billing patterns across healthcare claims; boosted fraud-flagging accuracy by 24% and reduced false positives by 30%. Engineered feature pipelines in SQL and PySpark, automating ingestion of 80 M+ daily claim records from disparate sources into a unified data mart for model training. Generated time-series forecasting models using ARIMA and Prophet to predict patient visit volumes and provider capacity, improving scheduling efficiency by 15%. Tuned hyperparameters via GridSearchCV and deployed trained models as REST APIs (Flask) integrated with existing dashboards, enabling real-time scoring and alerts. Collaborated with business and compliance teams to validate output under HIPAA constraints, ensuring secure handling of PHI while cutting manual review hours by 40%.