Machine Learning Data Scientist

Shravya Thaniparthi

Mail: ***@*********.***

LinkedIn: http://linkedin.com/in/sravyarao-237012185

SUMMARY

I have around 11 years of experience as a Data Scientist and expertise in Artificial Intelligence/ Machine learning Algorithms.

Good hands-on experience in Software languages with Python, and R Studio. Highly accurate and experienced in executing data-driven solutions to increase efficiency, accuracy, and utility of internal data processing adept at collecting, analyzing, and interpreting large datasets, developing new forecasting models, and performing data management tasks.

Experienced at creating data regression models, using predictive data modeling, and analyzing data mining algorithms to deliver insights and implement action-oriented solutions to complex business problems

Experience designing, developing, and testing Web Applications using HTML (4/5), CSS (2/3), JavaScript, Typescript, Angular, Node.js, jQuery, React, AJAX, XML, Bootstrap, JSON.

Proficient in machine learning frameworks and tools (e.g., TensorFlow, PyTorch, scikit-learn).

Using machine learning techniques supervised, unsupervised, reinforcement learning and understanding the requirement & design for AI/ML use cases

Experience with various ingestion techniques to bring into R, Python, and Azure ML environments from different big data platforms such as HDFS,

Strong hands and exposure to experience in Python, (Frameworks/libs: NumPy, SciPy, Pandas, NumPy, Matplotlib/Plotly, sci-kit learn, Stats models)

Hands-on experience in predictive analytics and statistical tools, machine learning algorithms, and big data tools

Implemented ethical considerations in generative AI (Gen AI) projects, Ex: Chat GPT, and Open AI addressing bias in training data and ensuring transparency in model decision-making to uphold responsible AI practices.

Utilize REST and AWS (Amazon Web services) in Redshift, and EMR for improved efficiency of Storage and proficiency in SQL databases MySQL, Oracle, and NoSQL databases MongoDB, Cassandra, and Oracle. Expertise in SQL stored queries.

Knowledge of healthcare-specific privacy and security regulations (e.g., HIPAA).

Involved in configuring CI/CD with Docker and Kubernetes.

Use pandas for data analysis and seaborn for statistical plots

Experience delivering products or solutions that utilized Machine Learning, Natural Language Processing, or other forms of AI (Artificial Intelligence) solutions like machine vision

Strong experience in SQL (using one of the database page admin (PostgreSQL), Cassandra, and Oracle) and Tableau

Visualized data using different visualization tools R, Azure ML, and Power BI

Experience with one Deep Learning (TensorFlow)

Sample data sets and scripts (HDFS commands, Hive sample queries, Pig sample queries, Data Pipeline sample queries)

Understand modern data architecture: Data Lake

Experience major components of Azure, know how to use Tensor Flow on the cloud, understand machine learning fundamentals

AWS and highly skilled in CNN, RNNs & LSTMs, Scikit Learn, Keras, and TensorFlow.

Certifications:

AWS Certified Machine Learning – Specialty.

Education:

Bachelor in Malla Reddy Engineering College, Computer Science - 2013

Technical Skills:

Machine Learning: Supervised, Unsupervised, Ensemble, Decision Tree etc.

Deep Learning: Artificial Neural Network, Convolutional Neural Network, Tensorflow, Keras, Natural Language Processing

Visualization: Power BI, Tableau

Cloud Platform: Azure, Google Cloud Platform, AWS

ETL: Informatica Power Center, Informatica Admin, Informatica Cloud, SSIS

Reports: Business Objects, SSRS

Data Base: Oracle, DB2, ASDW, SQL Server

Data Modeling: Data profiling, Data analysis, and modeling experience

OS: Windows, UNIX, Linux.

PROFESSIONAL EXPERIENCE

Client: LPL Financial, TX March 2022 – To Date

Role: Senior AI/Machine Learning Engineer

Responsibilities:

Worked on PostgreSQL (page Admin), Cassandra (DataStax), and SQL Developer tools to query and extract logs from BPM and MTAS database

Worked with Angular and typescript as part of the migration from Angular and vanilla JavaScript to Angular and React.

Analysed data and performed data preparation by applying a historical model on the data set in AZURE ML

Delivered result-oriented solutions by utilizing generative AI (Gen AI) to enhance creative processes, improve efficiency, and drive innovation across various projects.

Worked on Python libraries like NumPy, Pandas, SciKit Learn, math plot, seaborn, psycopg2, etc.

Using machine learning techniques supervised, unsupervised, and reinforcement learning and understanding the requirement & design for AI/ML use cases & Developing AI/ML algorithms

Demonstrated expertise in data preprocessing and cleaning using Azure ML tools.

Collaborated with cross-functional teams to identify and define business problems suitable for AI/ML solutions.

End-to-end analytical solutions to business problems. Understanding the problem, and data and creating an analytical solution using statistical techniques in Python or R and providing recommendations.

Effectively communicated complex generative AI (Gen AI) concepts and outcomes to both technical and non-technical stakeholders, facilitating a clear understanding of the value and impact of AI-driven initiatives.

Perform unit testing and provide system test support and validate & monitor deliverables in production

Leaded Kubernetes charts using Helm. Created reproducible builds of the Kubernetes applications, Kubernetes manifest files, and releases of Helm packages.

Hands-on experience with Azure ML SDK for Python, including managing datasets, creating experiments, and deploying models.

Automated the ML model building process by building Data Pipelines further integrating it with the Data cleaning process

Spearheaded the creation of innovative and visually striking content using generative AI (Gen AI) techniques, contributing to enhanced user engagement and brand recognition.

Machine learning model building collaborates with the team through GitLab integration.

Use Jira for project management teams such us report & analysis, workflow customization, issue, task management, and project customization and help teams of all types manage work

Designed and developed a data management system using MySQL, and SQL Built application logic using Python

Collaborated with cross-functional teams, integrating generative AI (Gen AI) into interdisciplinary projects to address complex challenges.

Improved fraud prediction performance by using random forest and gradient boosting for feature selection with Python Scikit-learn

Built the machine learning model including SVM, random forest, and XGboost to score and identify the potential new business case with Python Scikit-learn

Converted Azure ML procedures to PySpark scripts

Design elegant data visualizations to present complex analysis and insights to customers with Tableau or other related tools

Client: Sanford Health, MN August 2021 – March 2022

Role: Data scientist / Machine Learning Engineer

Responsibilities:

Developed and implemented machine learning models for medical image analysis, such as MRI or CT scans.

Applied natural language processing (NLP) techniques to extract valuable information from electronic health records (EHRs).

Integrated ML models into electronic health record systems to provide real-time insights to healthcare professionals.

Collaborate with ML Engineers and Data Scientists to build data and model pipelines and help in running machine learning tests and experiments

Used the AWS -CLI to suspend on Aws Lambda function and used AWS CLI to automate the backup of ephemeral data stores to S3 buckets EBS.

Ensured compliance with healthcare data privacy regulations, implementing secure and HIPAA-compliant ML solutions.

Communicated and coordinated with end client for collecting data and performed ETL to define the uniform standard format. Queried and retrieved data from Oracle database servers to get the dataset.

Experience with Statistical Modeling, Data Extraction, Data cleaning, Data screening, Data Exploration, and Data Visualization of structured and unstructured datasets

Experienced in Using Jenkins pipelines to drive all Microservices builds out to the Docker registry and then deployed to Kubernetes, Created Pods, and managed using Kubernetes.

Develop Machine Learning and NLP frameworks, models, and services that are flexible to extend to new features

Design elegant data visualizations to present complex analysis and insights to customers with Tableau or other related tools

Built web applications by using Python, Django, AWS, J2EE, PostgreSQL, MySQL, React, SQL Oracle, and MongoDB.

Proficient in programming languages such as Python, TensorFlow, PyTorch, and Keras, with a strong understanding of the underlying mathematical concepts.

Build and configure SQL and Excel data spreadsheets implanted into the business Strong hands-on experience with Microsoft “Office, and Excel. PowerPoint”

Integrated the AWS server with GitLab to push the model into production and monitor the performance

Ensured responsible and ethical use of generative AI (Gen AI) technologies, Ex: Chat GPT, and Open AI considering potential biases and societal implications in model development.

Client: Cognizant, India July 2016 – December 2020

Role: Data Scientist

Responsibilities:

Act as a business consultant for the use of Data Analytics to drive business decisions, business strategy

Successfully migrated the Django database from SQLite to MySQL to PostgreSQL with complete data integrity. Used Scala programming to perform transformations and apply business logic.

Using machine learning techniques supervised, unsupervised, reinforcement learning, and understanding the requirement

Excellent experience in ETL analysis, designing, developing, testing, and implementing ETL processes including performance tuning and query optimizing of database.

Wrote ANSIBLE Playbooks with Python, SSH as the Wrapper to Manage Configurations of AWS Nodes and Test Playbooks on AWS instances using Python. Run Ansible Scripts to provision Dev servers.

Experience in using Scikit-Learn and Stats models in Python for Machine Learning and Data Mining.

Translating business needs to technical requirements and implementation

Used predictive analytics such as machine learning and data mining techniques to forecast company sales of new products with a minimum 90% accuracy rate

Apply data science approaches and methodologies (liner and logistic regression decision trees) to improve business outcomes

Worked on Kubernetes (K8s) with Nvidia NGC containers using docker.

Applied machine learning in the analysis of clinical trial data for drug discovery and development.

Develop the data analysis model according to business scenarios

Evaluate the method and technical solution of data analytics projects

Design elegant data visualizations to present complex analysis and insights to customers with Tableau or other related tools

Analyze format data using a machine learning algorithm using Python kit Learn.

Prepares portfolio manager reports for assigned client review meetings.

Client: Sify Technologies, India December 2013 – July 2016

Role: Data Scientist

Responsibilities:

Tackled highly imbalanced Fraud dataset using under-sampling, oversampling with SMOTE, and cost-sensitive algorithms with Python Scikit-learn.

Wrote complex Spark SQL queries for data analysis to meet business requirements.

Developed MapReduce/Spark Python modules for predictive analytics & machine learning in AWS.

Worked on data cleaning and ensured data quality, consistency, and integrity using Pandas and NumPy.

Participated in feature engineering such as feature intersection generating, feature normalization, and label encoding with Scikit-learn preprocessing.

Improved fraud prediction performance by using random forest and gradient boosting for feature selection with Python Scikit-learn.

Performed Naïve Bayes, KNN, Logistic Regression, Random Forest, SVM, and XGboost to identify whether a loan will default or not.

Experience in working with Jenkins in a Docker container with EC2 slaves in an Amazon AWS cloud environment and familiar with surrounding technologies such as Mesos (Mesosphere) and Kubernetes.

Implemented Ensemble of Ridge, Lasso Regression, and XGboost to predict the potential loan default loss.

Contact this candidate