I am an AI/ML Engineer with 5 years of experience designing and deploying production-grade machine learning and Generative AI solutions across healthcare and enterprise domains, driving decision automation and operational efficiency. I build end-to-end ML systems using Python, PyTorch, TensorFlow, and Scikit-learn, delivering scalable predictive models that reduce manual intervention in critical workflows. I specialize in Transformers, deep learning architectures (CNNs, RNNs), and Retrieval-Augmented Generation (RAG), developing LLM-powered applications using LangChain, OpenAI APIs, and FAISS for context-aware intelligence. I implement robust MLOps practices with MLflow, Docker, Kubernetes, and CI/CD pipelines to enable reliable model deployment, monitoring, and reproducibility in AWS and Azure environments. I’m experienced in building distributed data pipelines with PySpark and Airflow, ensuring high-volume data processing and production model scalability.

Sai Supraja Ravi Kumar

I am an AI/ML Engineer with 5 years of experience designing and deploying production-grade machine learning and Generative AI solutions across healthcare and enterprise domains, driving decision automation and operational efficiency. I build end-to-end ML systems using Python, PyTorch, TensorFlow, and Scikit-learn, delivering scalable predictive models that reduce manual intervention in critical workflows. I specialize in Transformers, deep learning architectures (CNNs, RNNs), and Retrieval-Augmented Generation (RAG), developing LLM-powered applications using LangChain, OpenAI APIs, and FAISS for context-aware intelligence. I implement robust MLOps practices with MLflow, Docker, Kubernetes, and CI/CD pipelines to enable reliable model deployment, monitoring, and reproducibility in AWS and Azure environments. I’m experienced in building distributed data pipelines with PySpark and Airflow, ensuring high-volume data processing and production model scalability.

Available to hire

I am an AI/ML Engineer with 5 years of experience designing and deploying production-grade machine learning and Generative AI solutions across healthcare and enterprise domains, driving decision automation and operational efficiency. I build end-to-end ML systems using Python, PyTorch, TensorFlow, and Scikit-learn, delivering scalable predictive models that reduce manual intervention in critical workflows.

I specialize in Transformers, deep learning architectures (CNNs, RNNs), and Retrieval-Augmented Generation (RAG), developing LLM-powered applications using LangChain, OpenAI APIs, and FAISS for context-aware intelligence. I implement robust MLOps practices with MLflow, Docker, Kubernetes, and CI/CD pipelines to enable reliable model deployment, monitoring, and reproducibility in AWS and Azure environments. I’m experienced in building distributed data pipelines with PySpark and Airflow, ensuring high-volume data processing and production model scalability.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
See more

Language

English
Fluent

Work Experience

AI/ML Engineer at Optum
April 1, 2024 - Present
Owned the end-to-end ML lifecycle for a clinical risk-scoring platform processing 4M+ EHR, claims, pharmacy, and lab records, delivering real-time risk predictions for chronic disease management. Engineered HIPAA-compliant data pipelines (SQL + Python) and authored model lineage, audit logs, and PII-handling protocols, strengthening compliance readiness for internal audits. Developed production models (XGBoost, Gradient Boosting, BiLSTM) improving early-risk detection accuracy by 14%, reducing manual clinician triage and generating $1.2M annual cost savings. Deployed scalable model inference endpoints on SageMaker serving 18K+ predictions/day with <120ms latency, integrated with claims and care-management systems. Implemented drift detection, automated retraining workflows (Airflow), and alerting thresholds, reducing model performance degradation incidents by 40%. Applied SHAP/LIME for clinical explainability and interpretability validation. Collaborated with physicians, care managers,
AI/ML Engineer at Capgemini
January 1, 2020 - June 1, 2023
Developed supervised and ensemble ML models using Scikit-learn, XGBoost, and LightGBM on 2M+ customer records, improving churn prediction precision by 25%. Built deep learning solutions using TensorFlow and CNN architectures for behavioral pattern analysis, increasing campaign targeting efficiency by 19%. Engineered distributed data processing pipelines using Databricks, PySpark, and SQL, reducing processing time by 40%. Deployed containerized ML services using Docker and Kubernetes (AKS), supporting 100K+ API calls per day with 99% uptime. Implemented automated retraining and experiment tracking with MLflow and Airflow, reducing manual intervention by 60%. Designed scalable ETL/ELT workflows integrated with Snowflake and Azure ML, improving data consistency across business units. Conducted statistical validation and A/B testing using Python and NumPy, delivering a 15% lift in digital campaign conversions.

Education

Master of Science in Engineering Data Science at University of Houston
July 1, 2023 - May 1, 2025
Bachelor of Engineering in Electronics and Communication Engineering at GRT College, Anna University
June 1, 2018 - June 1, 2022
Master of Science in Engineering Data Science at University of Houston
July 1, 2023 - May 1, 2025
Bachelor of Engineering in Electronics and Communication Engineering at GRT College, Anna University
June 1, 2018 - June 1, 2022

Qualifications

AWS Certified Machine Learning – Specialty
January 11, 2030 - March 5, 2026
Microsoft Certified: Azure AI Engineer Associate
January 11, 2030 - March 5, 2026
Databricks Certified Machine Learning Professional
January 11, 2030 - March 5, 2026
Google Professional Machine Learning Engineer
January 11, 2030 - March 5, 2026
Azure AI 900
January 11, 2030 - January 5, 2026
IBM Data Science Professional Certificate
January 11, 2030 - January 5, 2026
AWS Certified Machine Learning – Specialty
January 11, 2030 - March 5, 2026
Microsoft Certified: Azure AI Engineer Associate
January 11, 2030 - March 5, 2026
Databricks Certified Machine Learning Professional
January 11, 2030 - March 5, 2026
Google Professional Machine Learning Engineer
January 11, 2030 - March 5, 2026

Industry Experience

Healthcare, Financial Services, Professional Services, Software & Internet, Other