Home

Srinath Putta - Sr.Data Scientist

[email protected]

Location: Chicago, Illinois, USA

Relocation:

Visa: H1B

SRINATH P Senior Data Scientist [email protected]| +1 602-773 1440 Sr. Data Scientist/Data Engineer PROFESSIONAL SUMMARY: Overall 9+ Extensive expertise in Data Science & Machine Learning, specializing in predictive modeling, time series forecasting, NLP, and deep learning. Applied supervised and unsupervised learning techniques such as Random Forest, XGBoost, SVM, KNN, Neural Networks, and Clustering for business-critical use cases including fraud detection, customer segmentation, and demand forecasting. Proficient in SQL, Python, and PySpark, with hands-on experience in big data processing, data warehousing, and ETL pipelines. Designed and optimized scalable data architectures leveraging AWS, Azure, and Google Cloud for real-time and batch processing workflows. Hands-on experience with Generative AI and LLMs, integrating GPT-4, BERT, and Hugging Face Transformers for NLP applications, including chatbots, sentiment analysis, text summarization, and automated document classification. Advanced data engineering capabilities, including building and managing ELT/ETL pipelines using Apache Kafka, Spark, Airflow, Snowflake, and Databricks, ensuring seamless data integration across structured and unstructured sources. Expert in SQL optimization and database management, working extensively with Teradata, Snowflake, PostgreSQL, and MySQL to enhance query performance and reduce processing times by 30%+ through advanced indexing and partitioning techniques. Experience in BI & Visualization, developing interactive dashboards using Tableau, Power BI, and Looker to translate complex datasets into meaningful business insights for stakeholders. Implemented time-series forecasting and anomaly detection models, using Prophet, ARIMA, and LSTMs to improve inventory management, churn prediction, and customer lifetime value analysis. Built and deployed ML models in cloud environments, leveraging MLOps frameworks and CI/CD pipelines using Docker, Kubernetes, and Terraform to automate model deployment and scaling. Worked with vector databases and search engines like Pinecone, Chroma, ElasticSearch, and AWS OpenSearch, integrating AI-driven solutions for personalized recommendations and semantic search. Designed and implemented knowledge graphs using Neo4j and AWS Neptune, enabling enhanced data linking, risk analysis, and pattern discovery for enterprise applications. Implemented feature engineering and dimensionality reduction techniques, leveraging AutoML, PCA, and feature selection methods to optimize model performance and interpretability. Worked extensively on Natural Language Processing (NLP) and text analytics, including entity recognition, sentiment analysis, and topic modeling using tools like NLTK, SpaCy, and TensorFlow. Optimized cloud data architectures, successfully migrating legacy SQL-based data warehouses to Snowflake and BigQuery, leading to 20-30% cost savings and improved performance. Applied advanced statistical methodologies, including Bayesian inference, Monte Carlo simulations, and causal inference techniques, to extract actionable insights from large-scale datasets. Developed recommendation engines and personalization systems for e-commerce and media clients, implementing collaborative filtering, content-based filtering, and hybrid recommendation models. Experience in anomaly detection and cybersecurity analytics, applying autoencoders, one-class SVMs, and graph- based anomaly detection techniques to identify fraudulent transactions and network intrusions. Strong software engineering skills, with experience in designing RESTful APIs, microservices, and backend data services using Flask, FastAPI, and Go for data-driven applications. Led and mentored teams of data scientists and analysts, fostering collaborative learning environments and ensuring successful execution of AI/ML projects aligned with business goals. Passionate about continuous learning, keeping up with the latest AI/ML advancements, Generative AI, and MLOps best practices, and integrating cutting-edge data science methodologies into business solutions. TECHNICAL SKILLS: Programming Languages: Python, SQL, R, Scala, Java, C++, Go, Julia Machine Learning & AI: Supervised & Unsupervised Learning, NLP, Deep Learning, Generative AI, Time Series Forecasting, Reinforcement Learning, Anomaly Detection, Graph Neural Networks, Explainable AI, Causal Inference Data Engineering: SQL, PySpark, Apache Kafka, Data Warehousing, ETL, Data Pipelines, Big Data Processing, Feature Engineering, Real-time Streaming, Data Lake Architecture, Event-driven Processing Cloud Platforms: AWS (S3, Lambda, Redshift, EMR, SageMaker, Step Functions, Glue), Azure (Data Factory, Synapse, Databricks, Logic Apps, Cognitive Services), GCP (BigQuery, AI Platform, Vertex AI, Cloud Functions, Cloud Run, Dataflow) Databases: Snowflake, Redshift, PostgreSQL, MongoDB, MySQL, Cassandra, Teradata, Neo4j, Elasticsearch, Pinecone, GraphQL, Firebase, DynamoDB Visualization Tools: Tableau, Power BI, Matplotlib, Seaborn, Dash, Plotly, Looker, D3.js, Superset, Google Data Studio Frameworks & Libraries: TensorFlow, PyTorch, Scikit-Learn, Hugging Face, Langchain, OpenAI API, XGBoost, LightGBM, LlamaIndex, AutoML, FastAPI, Spark MLlib, FlinkML, RAPIDS AI DevOps & CI/CD: Docker, Kubernetes, Git, Jenkins, Terraform, MLflow, Airflow, CI/CD Pipelines, Feature Store, Data Versioning, Continuous Monitoring, CloudFormation, Helm Big Data & Distributed Computing: Apache Spark, Hadoop, HBase, Hive, Presto, Databricks, Beam, Flink, Dask, Ray, Google Dataflow, AWS Glue, Delta Lake, Iceberg CERTIFICATIONS: Microsoft Certified: Azure Developer Associate Microsoft Certified: Azure Data Engineer Associate Amazon Web Services Certified Cloud Practitioner PROFESSIONAL EXPERIENCE: Optum, Minneapolis, MN January 2024 - Present Sr. Data Scientist/Data Engineer Responsibilities: Developed end-to-end machine learning models for customer segmentation, fraud detection, and risk assessment, resulting in a 30% improvement in operational efficiency. Designed real-time data pipelines using Apache Airflow, PySpark, and SQL, reducing ETL processing time by 40%. Built large-scale NLP models using BERT, GPT-4, and T5 for automated document summarization, reducing manual review time by 50%. Spearheaded predictive modeling initiatives for churn prediction and customer lifetime value analysis, increasing customer retention rates by 25%. Led the migration of legacy SQL-based data warehouses to Snowflake and Google BigQuery, improving query speeds by 3x. Implemented MLOps pipelines for continuous model training and deployment using Docker, Kubernetes, and Jenkins, cutting deployment time by 50%. Developed vector search solutions using Pinecone and ElasticSearch, enhancing semantic search accuracy for knowledge management systems. Designed LLM-powered chatbots with LangChain and OpenAI APIs to automate customer support, improving response accuracy by 35%. Built interactive dashboards using Tableau and Power BI, providing real-time business intelligence to executive leadership. Implemented A/B testing frameworks to optimize marketing campaigns, increasing conversion rates by 22%. Designed time-series forecasting models (ARIMA, Prophet, LSTMs) for sales and demand forecasting, reducing inventory shortages by 20%. Applied Graph Neural Networks (GNNs) for fraud detection, reducing fraud-related financial losses by 32%. Led a team of junior data scientists and engineers, mentoring them in data science best practices, cloud computing, and model deployment. Developed automated anomaly detection systems using Isolation Forests and Autoencoders, improving cybersecurity threat monitoring. Worked cross-functionally with engineering, marketing, and finance teams to align AI solutions with business objectives, leading to 20% higher efficiency in strategic decision-making. State of OK-DHHS, Oklahoma City, OK September 2021 December 2023 Data Scientist/Data Engineer Responsibilities: Designed ML models for customer retention and churn prediction using XGBoost, Random Forest, and Deep Learning, leading to an 18% reduction in churn rates. Developed real-time streaming pipelines with Apache Kafka and Spark Streaming, improving data ingestion performance by 50%. Built a recommendation engine using collaborative filtering and reinforcement learning, increasing user engagement by 28%. Implemented SQL query optimizations in Teradata and PostgreSQL, improving database performance by 40%. Deployed NLP-driven content classification models using spaCy and Hugging Face Transformers, automating document tagging and reducing processing time by 35%. Applied A/B testing and causal inference techniques to optimize pricing strategies, leading to a 15% increase in revenue per customer. Integrated Generative AI-based text summarization into business workflows, cutting manual documentation efforts by 50%. Migrated on-prem data warehouses to AWS Redshift and Snowflake, reducing infrastructure costs by 20%. Developed unsupervised anomaly detection models for fraud and transaction monitoring, reducing false positive alerts by 25%. Designed BI dashboards in Tableau and Power BI, empowering stakeholders with actionable insights. Automated ETL processes using Apache NiFi and Airflow, reducing data processing bottlenecks by 40%. Built customer sentiment analysis pipelines using NLP and social media analytics, improving customer engagement strategies. Led internal workshops on ML model interpretability, improving team competency in Explainable AI (XAI). Worked with business leaders to align AI solutions with revenue goals, leading to increased adoption of data-driven strategies. Webster Bank, Stamford, CT February 2020 August 2021 Data Scientist/Data Engineer Responsibilities: Conducted statistical data analysis using R and Python, uncovering trends that improved business strategy. Designed interactive Tableau dashboards to track KPIs and sales trends, enhancing executive decision-making. Built customer segmentation models using K-Means Clustering, improving targeted marketing campaigns. Automated data cleaning processes, reducing manual effort by 35%. Developed predictive analytics for sales forecasting, increasing forecasting accuracy by 18%. Designed SQL-based ETL pipelines for data aggregation and reporting. Conducted A/B testing for marketing campaigns, optimizing email conversion rates. Developed real-time reports in Power BI, enabling faster data-driven decisions. Created automated data ingestion pipelines, improving workflow efficiency. Applied sentiment analysis on customer feedback, helping to enhance product offerings. Led data governance initiatives, ensuring compliance with data privacy laws. Developed forecasting models for demand planning, improving inventory management. Built data-driven pricing strategies, increasing profit margins by 15%. Implemented SQL query optimizations, reducing query execution times by 50%. Provided data-driven recommendations to stakeholders, influencing strategic decisions. Amica Mutual Insurance, Lincoln, RI August 2018 January 2020 Data Analyst Responsibilities: Designed and implemented machine learning models in Python, including regression, classification, and ensemble techniques, to analyze historical financial data and improve forecasting accuracy by 25%. Built data pipelines using Apache Kafka to streamline data ingestion from multiple sources, enhancing data processing efficiency by 30%. Transformed and optimized large-scale datasets using Azure Databricks, ensuring seamless data integration into enterprise databases. Enhanced database query performance by 40% through advanced SQL query optimization techniques, significantly reducing data retrieval times. Developed financial, growth, and revenue-based reports using Power BI and Crystal Reports, driving a 15% increase in actionable insights for business stakeholders. Conducted A/B testing and experimentation to refine product features, leading to a 20% boost in user engagement and a 25% increase in conversion rates. Engineered CI/CD pipelines for MLOps using Terraform, implementing version control and automating machine learning workflows for scalability. Built a personalized recommendation system using collaborative filtering techniques, improving customer engagement and satisfaction by 20%. Generated ART reports by leveraging MySQL, SQL Developer, and MongoDB, facilitating comprehensive data analysis and reporting. Led initiatives in database migration, API development, and repository construction, integrating DNS mapping and increasing workflow efficiency by 40%. Automated data quality validation processes, reducing data inconsistencies and errors by 20%. Designed and deployed Azure-based ETL pipelines utilizing Data Factory and Databricks, reducing data processing time by 30% and saving 15 hours per week in manual tasks. Global Software limited, India July 2014 July 2017 Data Analyst Performed data profiling and exploratory analysis to assess user behavior across traffic patterns, location, and time, improving behavioral insights by 25%. Integrated Teradata with multiple data sources and platforms, enhancing data synchronization and reducing inconsistencies by 25%. Optimized machine learning model performance through cross-validation, log-loss evaluation, ROC curves, and AUC- based feature selection, increasing model accuracy by 30%. Leveraged Elastic Search and Kibana to improve model performance and real-time data retrieval efficiency. Conducted sentiment analysis and text classification on social media data, achieving 90% accuracy in polarity detection and improving customer satisfaction by 20%. Led the migration of two enterprise data warehouses from SQL Server to Snowflake and BigQuery, optimizing data architecture and achieving 22% cost savings. Enhanced Snowflake database performance by fine-tuning SQL queries, reducing query response times by 25% and boosting reporting efficiency by 20%. Streamlined data modeling and migration of 500+ tables containing 4 billion rows, improving operational efficiency by 40% and aligning with strategic data initiatives. Designed and deployed an interactive Tableau dashboard showcasing market and trade KPIs, reducing leadership decision-making time by 40%. Developed an internal budget approval system using Power Apps and Power Automate, automating workflows and reducing processing time by 40%, saving 20+ hours per week. Drove alignment between analytics projects and business objectives, delivering measurable improvements in fraud detection, credit risk assessment, and customer retention. Keywords: cplusplus continuous integration continuous deployment artificial intelligence machine learning javascript business intelligence sthree rlang golang Connecticut Minnesota Rhode Island