Open to new opportunities · United States

AmoghRamagiri

{ }

Data Scientist focused on shipping real ML systems: risk models, forecasting pipelines, and GenAI/RAG tooling. Currently a Master's student at George Washington University.

building systems that listen to data.

Data Scientist focused on shipping real ML systems: risk models, forecasting pipelines, and GenAI/RAG tooling. Currently a Master's student in Data Science at George Washington University. I care about the boring parts: clean data, honest metrics, and telling the truth about what a model can and can't do.

I care about the boring parts: clean pipelines, honest metrics, and interfaces that let humans stay in the loop. I've worked across risk modeling, sustainability analytics, and product, and I tend to ship the thing.

Good data science is 10% modeling and 90% telling the truth about what the data can and can't say.
Amogh Ramagiri
AMOGH.GR · 202635.2MM · ISO 200

where I've worked and studied.

A short trail of roles, research, and the occasional late-night pipeline fix.

work

May 2025 – Dec 2025Lancaster, PA
Data Scientist
Fulton Bank

Built a mortgage default prediction model (Random Forest) at 91% recall on high-risk applications. Led Azure (Data Factory, Synapse) migration and rebuilt 37+ Power BI dashboards on Microsoft Fabric.

PythonSQLRandom ForestAzure Data FactorySynapsePower BIMicrosoft Fabric
Mar 2024 – Aug 2024Bengaluru, India
Data Scientist
Factocart, Velabh Technologies Pvt. Ltd.

Built SKU-level demand forecasting (XGBoost, 92% accuracy), cutting stockouts 13%. Engineered features from 2M+ customer records and ran A/B tests that lifted conversion 15%.

PythonXGBoostRandom ForestAWS RDSA/B TestingFeature Engineering
Sep 2023 – Mar 2024Changhua, Taiwan
Research Scientist
Embedded System Lab, NCUE

Built a multi-modal biometric auth system (DeepFace + MFCC, PyTorch) for offline Raspberry Pi deployment, +30% accuracy over baseline. Edge-to-cloud pipeline streamed records with sub-200ms latency.

PyTorchDeepFaceMFCCFlaskREST APIsRaspberry PiEdge ML
Jun 2022 – Sep 2023Bengaluru, India
Data Analyst
Wodo

Automated marketing reporting across 13+ clients (~75% less weekly effort). Real-time dashboards cut wasted ad spend 20%, and clustering identified 5 high-value cohorts that lifted conversion 12%.

PythonSQLK-MeansClusteringDashboardsMarketing Analytics

education

Aug 2024 – May 2026Washington, DClive
Master of Science in Data Science
George Washington University

CCAS Dean's Award. Coursework in ML, statistics, large-scale data systems, and deep learning.

Machine LearningStatisticsDeep LearningData Systems
Sept 2020 – May 2024Bengaluru, KA
Bachelor of Technology, Computer Science & Engineering
Presidency University

AI/ML specialization. Coursework in algorithms, statistics, and computer vision, plus a capstone ML research project.

AI/ML SpecializationAlgorithmsComputer VisionResearch

things I've built.

A mix of shipped products, ML research, and experiments. Each one taught me something I couldn't learn from a course.

ml engineeringOct 2024
Energy Management System

Developed an interactive Streamlit app for analyzing university building energy data with ML models. Implemented Random Forest algorithms to identify consumption patterns.

deep learningMar 2024
Biometric Authentication System

Engineered dual-layer authentication system integrating DeepFace for facial recognition and MFCC features for voice recognition with 30% improved accuracy.

deep learningApr 2023
Leukemia Cancer Cell Classification

Researched and developed LDSVM (LR + DT + SVM) model for optimized prediction of Leukemia cancer cells using machine learning and deep learning techniques.

product / webAug 2025
Web Development Portfolio v3

Built responsive portfolio website using modern web technologies with interactive animations and optimized performance for showcasing professional work.

ml researchMay 2023
Credit Card Fraud Detection

Developed a credit card fraud detection model using supervised ML and ensemble methods (Logistic Regression, SVM, Random Forest, Bagging, Boosting). Achieved high accuracy with real-world data, minimizing false positives and boosting financial security.

what I work with.

Languages, frameworks, and habits I lean on daily. No prescription, just whatever matches the problem.

01Languages
PythonRSQLTypeScriptJavaScript
02ML / AI
Scikit-learnTensorFlowPyTorchXGBoostRandom ForestPySparkAirflow
03GenAI / RAG
LangChainOpenAI APIAnthropic APIpgvectorPineconePrompt Engineering
04Cloud / MLOps
AWS (EC2, S3, RDS, SageMaker)Azure (Data Factory, Synapse)DockerMLflowCI/CD
05Data Platforms
PostgreSQLSnowflakeDatabricksMongoDBSupabasePower BISSMS
06Product / Web
ReactNext.jsFlaskFastAPIREST APIsSupabase
PythonRSQLFlaskFastAPIPandasNumPyScikit-learnTensorFlowPyTorchPySparkAirflowLangChainRAGOpenAI APIAnthropic APIpgvectorPineconeAWSAzureDockerMLflowPostgreSQLSnowflakeDatabricksSupabasePower BIGit
PythonRSQLFlaskFastAPIPandasNumPyScikit-learnTensorFlowPyTorchPySparkAirflowLangChainRAGOpenAI APIAnthropic APIpgvectorPineconeAWSAzureDockerMLflowPostgreSQLSnowflakeDatabricksSupabasePower BIGit

let's build something.

Open to roles, collaborations, and interesting problems. Drop a line or grab a slot on my calendar.