Summary
Overview
Work History
Education
Skills
Projects
Achievements And Certificates
Timeline
Generic
Open To Work

R Srinivas Prabhu

Bengaluru

Summary

Offering solid foundation in data analysis and machine learning with keen desire to learn and grow in field. Delivers foundational understanding of Python, aiming to build upon this with advanced techniques and tools. Ready to use and develop data analysis and machine learning skills in Data Scientist role.

Overview

1
1
years of professional experience

Work History

Software Development Engineer

Amadeus Software Labs
07.2025 - Current

DevOps Intern

Amadeus
01.2025 - 06.2025
  • Automating multi-week infrastructure tasks at scale using Jenkins, Terraform, and GitOps, significantly reducing manual effort and boosting DevOps efficiency.
  • Automated 4+ repeatable infrastructure tasks using Jenkins, Terraform, and GitOps, reducing manual effort by ~90% and saving 2–3 weeks per task.

Data Science Intern

Kenvue
05.2024 - 07.2024
  • Enhanced demand forecasting accuracy for US and Canada markets through model optimization and demand classification, while building impactful visual reports and gaining supply chain domain insights.
  • Improved forecasting accuracy by 2–3% in Canada and 3–4% in the US through hyperparameter tuning and feature optimization for demand forecasting models.
  • Classified 1,000+ SKUs using ABC analysis and segmented demand patterns into Smooth, Intermittent, Erratic, and Lumpy categories, enhancing supply chain planning.
  • Built interactive Excel dashboards with pivot tables and charts, increasing clarity and usability for cross-functional teams by 50%.

Data Science Intern

Philips
04.2023 - 06.2023
  • Designed and optimized a binary classification pipeline on real-world healthcare data, enhancing model performance and generalization through advanced data fusion and imbalance mitigation.
  • Engineered a binary classification model from scratch using Random Forest and XGBoost, achieving 85–90% accuracy on real-time healthcare data.
  • Cleaned and merged 2 distinct datasets (survey + equipment) to create a unified training set, improving data usability and completeness by 30%.
  • Applied resampling techniques (e.g., SMOTE) to address class imbalance, leading to a 5–8% increase in model accuracy and improved AUC scores.

Education

Bachelor's Degree - Data Science and Engineering

Manipal Institute of Technology
Manipal, Karnataka
07.2025

Grade 12 - undefined

Madhav Kripa School
Manipal, Karnataka
01.2021

Grade 10 - undefined

Madhav Kripa School
Manipal, Karnataka
01.2019

Skills

  • Languages: C/C, Python, Scala, Java
  • Web Dev Technologies: HTML CSS JS, Flask, Streamlit, Oracle Database, Postgres
  • Libraries: Scikit-learn, TensorFlow, Pandas, NumPy, Gymnasium, Matplotlib, Langchain
  • Dev-Ops: Docker, Kubernetes, OpenShift, Jenkins, Terraform, Azure Fundamentals, GCP, Github Actions

Projects

Hit-and-Run Prediction (Research Paper | Ensemble Models | SMOTE)

  • Compare Model accuracy for imbalanced datasets with / without implementation of SMOTE.
  • Conducted a comparative analysis of 2 ensemble models (Random Forest,XGBoost) on 25,000+ real-time traffic crash records from the Chicago Data Portal.
  • Applied SMOTE, improving recall and overall accuracy by 7–10%, and reducing false negatives in hit-and-run classification.
  • Authored and presented research findings at the Microsoft CMT Conference, Egypt, showcasing the impact of SMOTE on model performance.


Demand Forecasting Dashboard (Time series | Demand forecasting | Timesfm )

  • Built a cloud-native forecasting system with FastAPI (REST API) and Streamlit (dashboard), enabling real-time demand predictions with .
  • Trained and deployed XGBoost and TimesFM (LLM) models, improving forecast accuracy by ~18% MAPE reduction vs baseline.
  • Automated end-to-end ML pipeline (data preprocessing, training, deployment) via GitHub Actions + Docker + GKE, cutting deployment time from hours to .
  • Scaled services on Kubernetes with health checks and Ingress, supporting 1k+ concurrent requests without degradation.


DeepGLO – Graph-based Time Series Forecasting Library

  • Developed a Python library for deep graph learning + time series forecasting, integrating matrix factorization for global patterns with Temporal Convolutional Networks (TCN) for local temporal modeling.
  • Delivered a scikit-learn–compatible API with modular, extensible design, enabling seamless adoption in ML pipelines.
  • Achieved state-of-the-art forecasting accuracy on multivariate time series benchmarks by jointly modeling inter-series correlations and temporal dependencies.
  • Optimized for research & production use, supporting scalable training and flexible experimentation across large datasets.

Achievements And Certificates

IBM Data Analyst Certificate

  • Mastered data cleaning, visualization, SQL, Excel, Python, and dashboard creation. Applied analytical skills to deliver actionable insights.

Timeline

Software Development Engineer

Amadeus Software Labs
07.2025 - Current

DevOps Intern

Amadeus
01.2025 - 06.2025

Data Science Intern

Kenvue
05.2024 - 07.2024

Data Science Intern

Philips
04.2023 - 06.2023

Grade 12 - undefined

Madhav Kripa School

Grade 10 - undefined

Madhav Kripa School

Bachelor's Degree - Data Science and Engineering

Manipal Institute of Technology
R Srinivas Prabhu