Hi, I'm Swaraj Chirumamilla, a data scientist with 4+ years of experience building machine learning models, AI-driven analytics solutions, and scalable data pipelines in financial services and enterprise analytics environments. I specialize in Python, SQL, Scikit-learn, TensorFlow, PyTorch, Spark, and cloud platforms like AWS, with hands-on work in Generative AI, large language models (LLMs), and Retrieval-Augmented Generation (RAG) to derive actionable insights and automate decision-making. I've delivered impact by improving forecasting accuracy, automating reporting operations, optimizing model performance, and deploying end-to-end ML solutions that support business growth and operational efficiency. I enjoy collaborating with cross-functional teams, building robust production pipelines with monitoring and retraining, and creating executive dashboards to drive informed decision-making.

Swaraj Chirumamilla

Hi, I'm Swaraj Chirumamilla, a data scientist with 4+ years of experience building machine learning models, AI-driven analytics solutions, and scalable data pipelines in financial services and enterprise analytics environments. I specialize in Python, SQL, Scikit-learn, TensorFlow, PyTorch, Spark, and cloud platforms like AWS, with hands-on work in Generative AI, large language models (LLMs), and Retrieval-Augmented Generation (RAG) to derive actionable insights and automate decision-making. I've delivered impact by improving forecasting accuracy, automating reporting operations, optimizing model performance, and deploying end-to-end ML solutions that support business growth and operational efficiency. I enjoy collaborating with cross-functional teams, building robust production pipelines with monitoring and retraining, and creating executive dashboards to drive informed decision-making.

Available to hire

Hi, I’m Swaraj Chirumamilla, a data scientist with 4+ years of experience building machine learning models, AI-driven analytics solutions, and scalable data pipelines in financial services and enterprise analytics environments. I specialize in Python, SQL, Scikit-learn, TensorFlow, PyTorch, Spark, and cloud platforms like AWS, with hands-on work in Generative AI, large language models (LLMs), and Retrieval-Augmented Generation (RAG) to derive actionable insights and automate decision-making.

I’ve delivered impact by improving forecasting accuracy, automating reporting operations, optimizing model performance, and deploying end-to-end ML solutions that support business growth and operational efficiency. I enjoy collaborating with cross-functional teams, building robust production pipelines with monitoring and retraining, and creating executive dashboards to drive informed decision-making.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
See more

Work Experience

Data Scientist at Freddie Mac
August 1, 2024 - Present
Increased mortgage delinquency prediction accuracy by 28% through machine learning models across enterprise lending datasets, reduced underwriting document review time by 45% via Retrieval-Augmented Generation pipelines, processed ~3 TB of structured mortgage data daily with PySpark, AWS Glue, Airflow, and Redshift, improved production model stability by 32% through deployment automation with AWS SageMaker, Docker, Kubernetes, and MLflow, lowered false-positive fraud investigations by 26% using anomaly detection, accelerated internal document retrieval via semantic search and vector indexing, reduced analytics query time by 37% via SQL optimization and cloud workflow tuning, delivered executive dashboards with Power BI and Tableau, improved underwriting recommendation consistency by 24%, and cut recurring reporting time by 50%.
Data Scientist at Hexaware Technologies
October 1, 2020 - December 1, 2022
Improved forecasting accuracy by 25% through predictive analytics; reduced manual ticket classification by 48% using NLP-based text analytics; processed high-volume structured and semi-structured datasets via cloud-based ETL with AWS, PySpark, and Airflow; increased recommendation accuracy by 22%; improved ML model reliability by 30% through feature engineering; accelerated KPI reporting generation by 35%; delivered analytics solutions within Agile timelines; enhanced leadership reporting with Power BI and Tableau dashboards; reduced repetitive reporting by 44% via Python-based workflow automation; improved production ML performance by 27% via retraining, monitoring, and deployment support across forecasting, classification, and reporting workloads.

Education

Master of Science, Computer Science at Midwestern State University
January 11, 2030 - December 1, 2024
Bachelor of Technology, Computer Science at SRM University
January 11, 2030 - June 1, 2022

Qualifications

Add your qualifications or awards here.

Industry Experience

Financial Services, Professional Services, Software & Internet

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
See more