Data Scientist (Bioinformatics)

• Aug 2017 - Present

Data Scientist

• Aug 2017 - Present

Responsibilities:• Understand business needs, design, create roadmap of execution. Architect the entire workflow from data inputs, preprocessing, analysis to outputs and data storage. Deploy data processing pipeline in production.• Manage the end-to-end lifecycle (build, validate, test and deployment) of machine learning models.• Identify data sources. Develop processes and tools to monitor and analyze model performance. • Mine, analyze data for improving products. Optimize data analysis processes and systems to improve efficiency and maintainability. • Interpret data and analyze results to derive insights and effectively communicate the insights for both scientific and business audience.• Document implementation. Coordinate with different functional team’s, guide and monitor team members.

Bioinformatics Engineer

• Nov 2013 - Jul 2017

Responsibilities: Data Analysis. 1. Pre processing of the raw NGS data, Structured and Semi Structured data. 2. Extract data from XML, JSON. Cleaning data. 3. Convert raw data into tidy data set for analysis. Merge data sets. 4. Perform explanatory analysis for understanding of data. 5. Design and develop pipelines to perform data analysis. 6. Perform statistical analysis and prepare analysis reports. 7. Regression analysis for estimating the relationships among variables. 8. Perform hypothesis testing, estimate confidence intervals, cluster analysis. Present and communicate the data insights/findings. 1. Create visualizations to aid in understanding data. 2. Use Base plotting system, Lattice plotting system and ggplots in R for generating various types of plots (Heat map, Scatter plots, Histograms etc) for data visualization. 3. Use kintr Markdown for generating reproducible reports. 4. Use open source tools, develop programs to organize and represent data in an understandable format, as well as assist in the preparation of scientific manuscripts. 5. Generate interactive plots using plotly. 6. Make interactive web applications using Shiny. Responsible for development of new bioinformatics tools for internal usage. Maintenance of various genome databases. Installation and maintenance of Local instance of UCSC Genome Browser.

Software Engineer

• Dec 2008 - Jul 2012

Responsibilities:1. Was working as associate technical consultant – Peoplesoft ERP Application. Worked with a team of highly motivated software engineers to deliver complex solutions to specific technical problems.2. Deeply involved in the designing, implementing, upgrading and maintaining of software to support various client’s Peoplesoft ERP.3. Designed and developed SQR, Application Engines, SQL for various client requirements.4. Handled data loads.5. Have worked on various databases - Oracle, DB2, SQL Server.6. Performed System Integration Testing, User Acceptance Testing.7. Client consulting, require gathering, training, and Q&A sessions.