Hruthik Kumar

About Hruthik Kumar

About Me I’m Hruthik, a Data Scientist | Data Engineer with 4+ years of experience building scalable data platforms and deploying machine learning solutions that drive business impact. My expertise spans data engineering, advanced analytics, and applied AI, making me equally comfortable designing data pipelines or developing predictive models. Key Highlights: Machine Learning & GenAI: Deployed predictive models (risk scoring, churn, readmission) using scikit-learn, TensorFlow, and AWS SageMaker. Explored Generative AI with Hugging Face for summarization, root cause generation, and insight copilots. NLP & Analytics: Designed NLP pipelines (Spark NLP, Python) to transform unstructured data into structured insights, enabling downstream analytics and leadership reporting. Big Data Engineering: Engineered pipelines with Spark, Databricks, Kafka, and AWS Glue to process high-volume data streams (100k+ events/sec, 10TB+ datasets) for real-time anomaly detection and analytics. Cloud & Warehousing: Experienced in Snowflake, AWS, and Azure for building modern, cloud-native data platforms. Experimentation & Insights: Applied A/B testing and statistical analysis to measure impact, and built dashboards (Tableau, Power BI) that convert complex outputs into clear business narratives. My Philosophy I believe data science and engineering work best together: robust pipelines ensure quality, while advanced analytics and AI turn that data into action. My goal is to bridge both worlds to deliver scalable, intelligent, and business-ready solutions. Always excited to collaborate, innovate, and push the boundaries of what’s possible with data. Let’s connect!

Experience

1. Data Scientist Data Engineer

   Toyota North America

   Aug 2024 — Present

   Developed and deployed ML models (scikit-learn, TensorFlow, SageMaker) for loan default and churn prediction, achieving 82% accuracy and integrating outputs into reporting workflows. Built a real-time anomaly detection system (Kafka + Spark Streaming) processing events/sec for instant fraud detection and risk scoring.• Automated feature engineering pipelines in SQL and Python to improve prediction accuracy and accelerate integration of insights into business reviews.• Leveraged AWS SageMaker to automate training, deployment, and monitoring of predictive models, improving portfolio analytics efficiency.• Designed and implemented scalable ETL workflows with AWS Glue and S3 to consolidate structured and semi-structured financial data, reducing processing time by 40%.