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

I'm Chandu Bhawani Kamma, a machine learning engineer with 5+ years of experience building production-grade ML, LLM, and RAG solutions in healthcare and enterprise environments. I enjoy crafting end-to-end ML systems using Python, PySpark, and modern tooling to turn data into reliable, scalable insights. I collaborate with clinicians and engineers to translate real-world needs into measurable ML products—reducing training and inference latency, supporting hundreds of production pipelines, and delivering impactful forecasting and resource optimization across 400+ distribution centers.…I'm Chandu Bhawani Kamma, a machine learning engineer with 5+ years of experience building production-grade ML, LLM, and RAG solutions in healthcare and enterprise environments. I enjoy crafting end-to-end ML systems using Python, PySpark, and modern tooling to turn data into reliable, scalable insights. I collaborate with clinicians and engineers to translate real-world needs into measurable ML products—reducing training and inference latency, supporting hundreds of production pipelines, and delivering impactful forecasting and resource optimization across 400+ distribution centers.

Chandu Bhawani Kamma

Data Scientist, AI Engineer, Full Stack Developer, +2





I'm Chandu Bhawani Kamma, a machine learning engineer with 5+ years of experience building production-grade ML, LLM, and RAG solutions in healthcare and enterprise environments. I enjoy crafting end-to-end ML systems using Python, PySpark, and modern tooling to turn data into reliable, scalable insights. I collaborate with clinicians and engineers to translate real-world needs into measurable ML products—reducing training and inference latency, supporting hundreds of production pipelines, and delivering impactful forecasting and resource optimization across 400+ distribution centers.…I'm Chandu Bhawani Kamma, a machine learning engineer with 5+ years of experience building production-grade ML, LLM, and RAG solutions in healthcare and enterprise environments. I enjoy crafting end-to-end ML systems using Python, PySpark, and modern tooling to turn data into reliable, scalable insights. I collaborate with clinicians and engineers to translate real-world needs into measurable ML products—reducing training and inference latency, supporting hundreds of production pipelines, and delivering impactful forecasting and resource optimization across 400+ distribution centers.

Available to hire

I’m Chandu Bhawani Kamma, a machine learning engineer with 5+ years of experience building production-grade ML, LLM, and RAG solutions in healthcare and enterprise environments. I enjoy crafting end-to-end ML systems using Python, PySpark, and modern tooling to turn data into reliable, scalable insights.

I collaborate with clinicians and engineers to translate real-world needs into measurable ML products—reducing training and inference latency, supporting hundreds of production pipelines, and delivering impactful forecasting and resource optimization across 400+ distribution centers.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Machine Learning Engineer at McKesson USA

July 1, 2024 - Present

Designed, trained, and deployed end-to-end ML and deep learning pipelines supporting classification, forecasting, and anomaly detection models across healthcare and logistics units. Built and optimized LLM-powered solutions, including RAG pipelines with LangChain, FAISS/Pinecone vector databases, and text-embedding models for scalable clinical text analytics and knowledge retrieval. Engineered production-grade ML systems with Databricks, PySpark, Delta Lake, and MLflow, reducing training and scoring latency by 45% and ensuring reproducible model lifecycle management. Developed automated data quality, drift detection, and monitoring frameworks integrating PySpark, Airflow, Azure Functions, and MLflow Model Registry across 90+ production pipelines. Implemented scalable feature engineering and ELT/ETL pipelines across Azure Synapse, Snowflake, SQL Server, and Databricks processing 4TB+ of multi-source data daily. Deployed containerized ML microservices using FastAPI, Docker, Kubernetes, a

Data Engineer – Research Assistant at University of Texas at Arlington

February 1, 2023 - May 1, 2024

Processed multi-terabyte patient and population datasets on Hadoop and Spark clusters, executing MapReduce/analytics to accelerate public-health research. Modernized predictive and statistical models using Python, R, and scikit-learn, analyzing 45K+ anonymized patient records to forecast treatment outcomes and optimize resource allocation. Integrated clinical and demographic datasets within AWS EMR and PostgreSQL, constructing ETL pipelines for structured data curation across seven academic teams. Designed interactive dashboards in Tableau and Power BI visualizing readmission rates, intervention efficacy, and medical cost trends to support faculty research and coursework. Maintained secure, version-controlled repositories and database environments, automating backups for 12 concurrent projects.

Machine Learning Engineer at Zomato India

January 1, 2021 - December 1, 2021

Developed end-to-end ML pipelines processing 2M+ daily transactional records to deliver real-time restaurant performance insights. Built and optimized predictive and statistical models for customer retention, order forecasting, and revenue optimization, improving decision-making for marketing and pricing. Engineered data transformation and feature engineering workflows across CRM, payments, and logistics datasets, consolidating data into lakehouse architectures on Azure and Snowflake for downstream ML/LLM applications. Created interactive dashboards translating model outputs into actionable insights for leadership and operations. Implemented pipeline automation, monitoring, and data quality frameworks using PySpark, Airflow, and MLflow to ensure reliable production ML workflows.

Data Engineer at Dell Technologies India

August 1, 2019 - December 1, 2020

Built and optimized scalable ETL/ELT pipelines using Python, SQL Server, PySpark, Databricks, and Delta Lake, processing 5M+ records daily to support analytics, ML, and LLM workflows. Developed data transformation, validation, and anomaly detection frameworks to ensure high-quality datasets for enterprise dashboards and ML models. Integrated multi-source enterprise data into lakehouse architectures on Azure, Snowflake, and SQL Server, enabling seamless downstream analytics. Designed forecasting, variance, and predictive models for product demand, warranty utilization, and operational planning. Implemented data governance, metadata standards, and pipeline monitoring to reduce discrepancies across nine systems and improve reliability.

Data Engineer – Research Assistant at The University of Texas at Arlington

February 1, 2023 - May 1, 2024

Processed multi-terabyte patient and population datasets on Hadoop and Spark clusters, executing MapReduce workflows to accelerate public-health analytics. Modernized predictive models using Python, R, and scikit-learn, analyzing 45K+ anonymized patient records to forecast treatment outcomes and optimize resource allocation. Integrated clinical and demographic data within AWS EMR and PostgreSQL, constructing ETL pipelines to improve data availability for multiple academic teams. Designed interactive dashboards in Tableau and Power BI to visualize readmission rates and intervention efficacy, supporting faculty research and coursework. Maintained secure, version-controlled repositories and environments with Git, SQL Server, and T-SQL, automating backups and ensuring data integrity for 12 concurrent projects.