Experience

Embark Veterinary

• United States
• Biotechnology Research
• 100 - 200 Employee

• Senior Engineering Manager

  • Aug 2022 - Present

  * Collaboration with scientists and statisticians on training and testing machine learning models that are capable of predicting traits and health outcomes in dogs * Interface with Business Intelligence and Product teams to identify requirements and design data delivery modules * Supervision of team of software engineers who containerize and deploy trained machine learning models into predictive workflows for traits and health outcomes in over 1 million dogs * Leadership on initiatives to: a) Develop machine learning models to identify causal genetic variants and to make predictions on ancestry, age, and probabilities of specific health outcomes, b) Migration of terabytes of files containing genomic data into a cloud-based database that could answer real-time queries and perform batch-mode analysis, resulting in significant (>50%) savings in data storage and transfer costs and analysis times, c) Infrastructure engineering for the scalability and reliability of machine learning models (ML-Ops) and d) Streamline design of gene panels using newly identified targets Governance of corporate data assets Show less



Northeastern University

• United States
• Higher Education
• 700 & Above Employee

• Parttime Lecturer

  • Feb 2020 - Present

  Instruction of Graduate Level courses in Data Analytics at the College of Professional Studies at Northeastern University Instruction of Graduate Level courses in Data Analytics at the College of Professional Studies at Northeastern University



ImmuneID

• United States
• Biotechnology Research
• 1 - 100 Employee

• Senior Director

  • Nov 2021 - Jun 2022



Multiple Myeloma Research Foundation - MMRF

• United States
• Non-profit Organizations
• 1 - 100 Employee

• Director, Bioinformatics

  • Aug 2020 - Nov 2021

  * Architected a cloud-agnostic data lake - the MMRF Data Lake - to integrate ~6 petabytes of genomic, immunogenic, PRO, and linked longitudinal clinical data sourced from thousands of multiple myeloma patients as part of research studies sponsored by the MMRF * Architected a sandbox that allows authorized investigators to develop reusable, containerized workflows using Jupyter Notebooks and R-Studio directly against the integrated genomic, immunogenic, and clinical data content of the MMRF Data Lake * Designed and implemented data delivery modules for requirements identified by patient outreach and marketing teams * Identified and worked with vendors to deliver various projects sponsored by the MMRF Show less



Harvard Medical School

• United States
• Higher Education
• 700 & Above Employee

• • Apr 2018 - Aug 2020

  ● Developed ETL pipelines for genomic and clinical data integration for biomedical research platforms: i2b2/tranSMART, PIC-SURE, and the National Institutes of Health’s DataSTAGE ● Implemented supervised and unsupervised machine learning techniques to identify o Patterns of clinical phenotypes and genotypes for stratification of patient cohorts o Highly predictive combinations of clinical phenotypes for genetic disorders such as 22q13 Syndrome, Sickle Cell Disease, and PTEN Hamartoma Tumor Syndrome Show less

• • Mar 2015 - Apr 2018

  ● Developed schema mappings between i2b2, PCORI CDM, and NIMH RDoC data models for data interoperability ● Developed querying and analysis modules for whole exome sequencing data in VCF and BAM files● Developed comparative statistical and machine learning tools for establishing correlations between genotype and phenotype data, as well as for the stratification of patient phenotypes and genotypes, ● Deployed NLP engine for named entity recognition (NER) and contextual information from rich-text clinical notes of patients including negation and uncertainty Show less



AstraZeneca

• United Kingdom
• Pharmaceutical Manufacturing
• 700 & Above Employee

• Consultant, Translational Genomics Group

  • Aug 2017 - Jan 2018

  Project: Genomics Data Integration and Search SUMMARY: Developed a customized ontology-based search engine for the translational genomics group PROBLEM: The translational genomics group had their data and their analysis results in diverse locations. Performing searches was complex and time-intensive SOLUTION: Developed an ontology-based data integration and search solution that incorporated several search modalities for the group, cutting down search time from hours to minutes (and sometimes seconds). As part of this project: * In collaboration with the team lead and other consultants, I developed an ontology - formalizing existing descriptions about the different datasets that were collected on an Excel spreadsheet – containing explicit associations between the different datasets, making them amenable to integration * After some research, I adopted and deployed an open source toolkit capable of transforming metadata in Excel spreadsheets into a simple RDF ontology, containing the associations outlined in my ontology design work (see above) * I transformed the raw genomics and analysis pipeline data into RDF format using the toolkit and loaded this data into an instance of a Sesame RDF triple store * For each search use case, I developed and tested SPARQL queries for the data in the RDF triple store * I leveraged and adapted backend tools such as Apache Bootstrap and front-end toolkits such as Angular JS to create a Web user interface from which users could enter search parameters and browse through the returned results Show less



The Ohio State University Wexner Medical Center

• United States
• Hospitals and Health Care
• 700 & Above Employee

• Postdoctoral Researcher in Biomedical Informatics

  • Feb 2014 - Mar 2015

  ● Developed pipelines for integration of SNP, CGH, NexGen sequence, and karyotype data with clinical phenotype data from leukemia patients for identifying cross-correlations that can lead to improved prognosis and therapy ● Benchmarked performance of Semantic Web compatible NoSQL graph databases for querying and analyses of cancer data against RDF Triple Stores and conventional Relational Databases ● Developed a novel knowledge discovery methodology for connecting researchers from different disciplines using graph exploration techniques Show less



TopQuadrant

• Software Development
• 1 - 100 Employee

• Sr Semantics Engineer

  • Mar 2012 - Nov 2012

  ● Curated enterprise ontologies from NASA to meet QA standards ● Architected a Java concurrency framework layered upon the TopBraid ontology development platform ● Consulted on “omics” data integration prototype for corporate customers ● Curated enterprise ontologies from NASA to meet QA standards ● Architected a Java concurrency framework layered upon the TopBraid ontology development platform ● Consulted on “omics” data integration prototype for corporate customers



School of Engineering and Technology, IUPUI

• United States
• Higher Education
• 1 - 100 Employee

• Visiting Faculty

  • Jul 2011 - Feb 2012

  ● Research into ○ Semantic Web Service Oriented Architectures (SOA) for Heterogeneous Sensor Annotation, Dynamic Invocation, Data Integration and Dynamic or Manual Process Workflow Composition ○ Parallel architectures (GPGPU) for efficient alignment of high throughput biological sequences ● Research into ○ Semantic Web Service Oriented Architectures (SOA) for Heterogeneous Sensor Annotation, Dynamic Invocation, Data Integration and Dynamic or Manual Process Workflow Composition ○ Parallel architectures (GPGPU) for efficient alignment of high throughput biological sequences



Malla Software Technologies Private Limited

• IT Services and IT Consulting
• 1 - 100 Employee

• Director

  • Dec 2010 - Jun 2011

  * Technical leadership on all training and software development projects at MallaSoft * Management of a team of software developers and managers on Java and .NET platforms * Supervision of training of more than 500 students in industrial software development technologies * Streamlined business processes at MallaSoft by: • deployment of project management tool and training of developers • deployment of project wiki and content management tools • architecting in house software applications as part of an automation initiative Show less



University of North Carolina at Chapel Hill

• United States
• Higher Education
• 700 & Above Employee

• Applications Specialist

  • Aug 2008 - Jun 2010

  * Design, implement, test, optimize, deploy, and document software to: • load genome and phenotype data from multiple sources into translational database • analyze data and discover new relationships in integrated data • query data for export to web services interface * Develop innovative approaches to problem solving using open source software * Automate scalable analysis techniques using SQL to ensure data quality. * Periodically generate data summary reports and data quality reports * Periodically perform robustness/strength testing using Apache JMeter * Advise project stakeholders on all data related aspects of the project * Interact with end user experts in phylogenetics, biogeography, paleobiology, systematics etc * Publish details of software in technical reports as well as at conferences and journals Show less



The University of British Columbia

• Canada
• Higher Education
• 700 & Above Employee

• Post Doctoral Fellow

  • Aug 2006 - Jun 2008

  ● Developed an ontology-based annotation and classification prototype for images of leukocytes. ● Developed an annotation framework for research publications to use terms from ontologies. ● Collaborated on development of two significant biomedical ontology development initiatives: Ontology for Biomedical Investigations (OBI) for biomedical experiments, and BioPAX for biological pathways ● Developed an ontology-based annotation and classification prototype for images of leukocytes. ● Developed an annotation framework for research publications to use terms from ontologies. ● Collaborated on development of two significant biomedical ontology development initiatives: Ontology for Biomedical Investigations (OBI) for biomedical experiments, and BioPAX for biological pathways



Neumont College of Computer Science

• United States
• Higher Education
• 1 - 100 Employee

• Assistant Professor

  • Jan 2006 - Jul 2006

  * Taught undergraduate CS courses in algorithms and data structures & Java programming. * Supervised and mentored student workers working on live content management project * Taught undergraduate CS courses in algorithms and data structures & Java programming. * Supervised and mentored student workers working on live content management project



CDI Engineering Solutions

• United States
• Services for Renewable Energy
• 700 & Above Employee

• Web Developer

  • Mar 2001 - Nov 2001

  * Developed an intranet wide digital library application (Klio) for storage and access of digital media including high-resolution images for the Creative Services Division of IBM Inc. * Developed an intranet wide digital library application (Klio) for storage and access of digital media including high-resolution images for the Creative Services Division of IBM Inc.



FedEx Services

• Truck Transportation
• 700 & Above Employee

• Java/JSP Developer (Intern)

  • Aug 2000 - Dec 2000

  * JSP application development to summarize and tabulate data from distributed databases and LDAP directories * JSP application development to summarize and tabulate data from distributed databases and LDAP directories