Evan Clark

Worked closely with the Wadsworth Center at the New York Department of Health, porting their workflows for bacterial and viral NGS processing onto GCP and Nextflow. Developed custom Python applications that automate several manual processes, including launching batch compute resources and generating automatic build pipelines for custom toolkits.

Migrated existing Python-based workflows to Nextflow for Roche's new SBX sequencing pipeline, leveraging multi-site compute environments. Developed best practices for versioning and containerizing workflows, integrating them into production toolchains. Collaborated with engineers and project owners to meet specific requirements, maximizing efficiency and minimizing cost.

Spearheaded initiatives to develop novel products and solutions as the lead operations personnel and research engineer. Led a team in developing several graphics applications for internal production use and to support the broader Virtual Production community through open-source initiatives. Actively led project development proposals for technology partners including HP, Canon, Nvidia, Apple, and I

Collaborated with a team of software engineers, terminologists, researchers, and bioinformaticians to maintain the MSK Extract application. Leveraged Kubernetes to build a cloud-native deployment of the application for unified production and development. Implemented a central gRPC-based message queue for sending and receiving data updates across multiple applications utilizing Protobuf contracts.

Developed a video streaming service using NodeJS, Swift, Nginx, and Python, aimed at providing copyrighted content securely and easily to event venues and restaurants. My primary role was the design of a mobile streaming platform, website, and server-side architecture. Additionally, engineered the cloud services necessary to provide DNS resolution and content caching to optimize performance.

Facilitated the development and deployment of bioinformatics pipelines and applications to manage and execute workflows for precision medicine in clinical production within the multiple myeloma group. Specialized in ETL, AWS cloud engineering, biological data processing, and machine learning model development. Became an active contributor to CWL and the Arvados distributed genomics platform, and p

Developed a pipeline for the generation of De Novo assemblies for organisms with poorly characterized genomes. Generated and annotated these assemblies using databases that included UniProt and RefSeq. Additionally, was involved in the development of a tandem sequencing/Mass Spectrometry approach to analyze novel peptides.

Developed novel solutions based around deep learning frameworks to solve complex issues using big-data. Primarily focused on developing early detection platforms for cancer using next-generation sequencing. Also developed software to better understand the physical mechanisms that regulate protein folding for synthetic biology applications.

Developed a university-wide analysis platform for genomics and big-data mining, including pipelines for RNA-Seq analysis, in partnership with FAU’s High-Performance Computing division. This project served as a sandbox for students to experiment with publicly available datasets and learn the engineering, computational, and biological aspects required for high-level bioinformatic research.

Had first-hand experience working with the admissions team, assisting in streamlining the student application review pipeline and designing an interview recording and review system. Designed and developed marketing material for the institution. Deployed a distributed video rendering service for student media labs and created learning materials for undergraduate courses.