Bala Sai Krishna Madduluri
716-***-**** Newyork ***********************@*****.*** linkedin.com/in/balu-madduluri/ PROFESSIONAL SUMMARY
Experienced Data Scientist with 6+ years of experience in designing and deploying end-to-end machine learning pipelines, natural language processing (NLP), and advanced statistical modeling to drive data-driven decision-making. Proven expertise in deep learning frameworks (TensorFlow, PyTorch), cloud-native AI solutions
(AWS, Azure), and scalable data architectures. Adept at leading cross-functional teams to deliver AI/ML-driven products that improve operational efficiency and business outcomes. TECHNICAL SKILLS
Programming Languages: Python (NumPy, Pandas, Scikit-learn, TensorFlow, PyTorch, LangChain), R (Tidyverse, Caret), SQL (MySQL, PostgreSQL, Redshift), Ruby (Rails) Cloud Platforms: AWS (SageMaker, EC2, S3, Lambda, RedShift, Fargate, Step Functions), Azure (HDInsight, Data Factory, Synapse Analytics), GCP (BigQuery, Vertex AI) DevOps & Tools: React.js, Angular.js, Node.js, Git/GitHub Actions, Postman API, Jira, Jenkins, Docker, Kubernetes, Terraform, CI/CD Pipelines
Data Science & ML: DBMS (MySQL, PostgreSQL), NoSQL (MongoDB, Cassandra), BigQuery, Hadoop, Apache Spark, Scikit-learn, TensorFlow, PyTorch, Keras, XGBoost, Artificial Intelligence, Recommendation Systems, Predictive Analytics, Deep Learning (CNN, RNN, GANs), Neural Networks, NLP (BERT, GPT, T5, LangChain), Computer Vision
(YOLOv8, EfficientNet), Data Mining, ETL/ELT Pipelines, Data Wrangling, Feature Engineering Business Intelligence: Tableau, Power BI, Looker Studio, SAS, RPA, Business Strategy, Business Analytics, Market Analysis, Product Analytics, Product Management, Mathematics, Statistics PROFESSIONAL EXPERIENCE
Data Scientist
Emfoi Inc – Virginia, USA August 2024 - Present
Project Description: AI for Healthcare - Spearheaded the development of an AI-powered solution for classifying dental treatment data, reducing human error and enhancing diagnostic workflows.
● Designed and implemented deep learning models (EfficientNet, ResNet) using TensorFlow and PyTorch for anomaly detection in dental x-rays, achieving 86% accuracy and reducing diagnostic errors by 25%.
● Developed a (LLM)-based text-generation pipeline using GPT and T5 architectures, automating patient report creation and reducing documentation time by 30% while ensuring HIPAA compliance.
● Architected Node.js microservices for real-time model inference, achieving low-latency predictions (<200ms) and scaling to handle 10,000+ concurrent requests.
● Built a React-based interface for real-time anomaly detection and heatmap visualization, reducing diagnosis time by 40%, and an Angular-based admin dashboard to manage user access, model configurations, and data-annotation workflows.
● Utilized Docker and Kubernetes for containerization and orchestration, with back-end data pipelines using SQL and NoSQL solutions, optimizing data structures for scalable deployment.
● Implemented MLOps pipelines using MLflow and Kubeflow to streamline model deployment, monitoring, and retraining, reducing model drift by 20% and improving system reliability. Data Scientist
Svaary INC – Texas, USA September 2023 - July 2024 Project Description: Real-time Video Analytics - Designed an analytics platform capable of processing large-scale video data in real time, improving operational efficiency and decision-making.
● Built a real-time object detection system using YOLOv8 and deployed it on AWS EC2 and SageMaker, achieving 95% accuracy in helmet detection and improving workplace safety compliance by 40%.
● Designed a text-generation pipeline leveraging T5 and GPT-based models to produce real-time incident summaries, reducing manual reporting efforts by 50% and improving operational efficiency.
● Developed an Angular-driven dashboard for security teams to visualize live detection feeds, track compliance metrics, and configure AI model parameters.
● Created Node.js microservices to handle RESTful APIs for both real-time detection events and text-generation, ensuring seamless integration with front-end and back-end systems.
● Automated ETL pipelines using AWS Lambda, Fargate, and Step Functions, reducing operational costs by 30% and employing Docker and Kubernetes for production-grade AI services. Data Scientist
Scale AI - Buffalo, NY, USA February 2024 - July 2024
● Optimized performance of large language models (LLMs) by integrating human-based reinforcement learning strategies, achieving relevance and accuracy to the prompt.
● Developed a data pipeline with a prompt to improve model relevance to user prompts, enhancing user experience and model performance.
Data Engineer
Awign Enterprises Pvt Ltd – Bangalore, India (WOW Award for Excellence)February 2019 - December 2021 Project Description: Developed scalable ETL pipelines and migrated data enhancing query performance and automated alerting systems to improve data processing efficiency.
● Led the design and implementation of scalable data warehousing solutions using Azure Synapse Analytics and AWS Redshift, reducing operational costs by 30% and automating ETL pipelines to process 1M+ data points daily with 99.9% accuracy.
● Applied database design principles to implement MySQL and NoSQL solutions, optimizing query performance by 40% and ensuring data integrity for high-volume transactions.
● Built and maintained BI dashboards using Power BI, Tableau, and BigQuery, delivering key performance indicators (KPIs) to 60+ projects and enabling actionable insights that saved 40+ man-hours per week.
● Led cross-functional teams to deliver over 100 data-driven projects, enhancing productivity by 20% through effective project management and Agile methodologies in alignment with Azure DevOps. Business Analyst
Ranal Software Solutions Pvt Ltd – Bangalore, India June 2017 - January 2019 Project Description: Accelerated data analysis using SQL and Excel, providing key insights for executive decisions for 8 applications, ensuring successful project outcomes and high pass rates.
● Applied advanced data analysis techniques using SQL to generate reports and insights, supporting data-driven decision-making for senior management.
● Conducted user acceptance testing (UAT) to ensure business requirements were met, facilitating smooth project implementation and post-launch review.
● Delivered presentations to senior leadership, providing clear communication of business requirements, progress, and insights for strategic decision-making.
EDUCATION
University at Buffalo, State University of New York January 2022 - June 2023 Master of Professional Studies, Data Sciences and Applications Coursework: Machine Learning, Probability & Data Analysis, Statistical Data Mining, Numerical Analysis, Data Structures & Algorithms, Probability & Data Analysis, Database Management Systems, Cybersecurity, Python Programming, Bayesian Networks LEADERSHIP AND KEY CONTRIBUTIONS
● Event Organizer: Managed events with 40+ participants, showcasing leadership and organizational skills.
● Rotary Club Volunteer: Actively contributed to community fundraising and outreach initiatives. CERTIFICATIONS
-Microsoft Certified: Azure Data Scientist Associate Certification #: C6AE7B-6BI446
-IBM Data Science, Google Data Analytics Capstone