Shayon Keating Resume

Education

Northeastern University

Boston, MA

Georgia Institute of Technology

Atlanta, GA

University of Georgia

Athens, GA

Relevant Technical Coursework:

  • Collect-Store-Analyze Data (DA5020)
  • Data Structures and Algorithms (CS5800)
  • Bioinformatics Programming (BINF6200)
  • Computational Methods 1 (BINF6308)
  • Computational Methods 2 (BINF6309)
  • Statistics for Bioinformatics (STAT6200)
  • 'Omics in Bioinformatics Programming (BINF6420)
  • Co-op Work Experience (BINF6964)
  • Ethics in Biological Research (BIOL6381)
  • Probability and Statistics (STAT2000)

Technical Skills

  • Languages: Python, SQL, Linux/Bash, Javascript, Typescript, CSS, HTML
  • Libraries: pandas, matplotlib, numpy, pytorch, tensorflow, scikit-learn, pyspark
  • Frameworks: react, node.js, next.js, react-native, d3, svelte kit, flask
  • Developer Tools: Git, Docker, Visual Studio, Jupyter Notebook
  • Data Tools: AWS, Azure, Snowflake, Spark

Professional Experience

Data Engineer III at Tetrascience

July 2024 – Current Remote, USA

  • Tetrascience is a scientific data and ai cloud company that liberates, unifies, and transforms your raw data into more-than-FAIR, AI-native data for scientific use cases.

Data Analyst - Internship at Kimberly Clark Corporation

April 2024 – July 2024 Remote, USA

  • Kimberly-Clark Professional is the B2B division of Kimberly-Clark, providing hygiene, cleaning, and safety products for businesses and workplaces.
  • Developed and integrated sustainability metrics for KMB Family Care, enabling real-time tracking of key sustainability goals. Sourced and cleaned data from SAP, then built an automated ETL pipeline to feed a Power BI dashboard hosted on Azure. The dashboard provided Directors/Managers with an at-a-glance view of quarterly sustainability performance.
  • Analyzed IoT Bluetooth battery data to assess the voltage drain caused by Bluetooth devices on smart restroom technology. Implemented a batch processing pipeline using Kafka for data ingestion and Spark for processing. Developed a scalable solution using Azure Data Lake for storage and PostgreSQL for storing and querying device IDs, enabling determination of voltage drain per update.

Principal Associate Scientist at Strand Therapeutics

April 2023 – February 2024 Boston, MA

  • Strand Therapeutics is an early stage genetic medicine company focused on delivering mRNA circuits to the body. I worked on the delivery side of the company.
  • Developed a drug product tracking database, enhancing R&D data management through automated data retrieval of structured and unstructured data via ETL processes, leveraging Lambda and S3. This initiative supported data-driven decision-making between the executive team and R&D, aligning with the company’s product development roadmap for tumor targeting therapeutics.
  • Developed an internal app on top of the drug product database using Next.js, enabling real-time tracking of metrics and visualizations.
  • Led the design and execution of automated nanoparticle assays using robots, significantly reducing R&D time from 10 to 2 hours a week and fostered a data-centric approach to product development. Integrated data from Benchling into Azure Data Lake.

Research Associate II at Poseida Therapeutics

January 2022 – April 2023 San Diego, CA

  • Poseida Therapeutics is clinical stage biopharmaceutical company focused on developing gene and cell therapies using a non viral delivery platform.
  • Led screening efforts of a 10,000+ chemical library by automating data analysis for a high-throughput multi-dimensional assay. Utilized jupyter notebooks, pandas, scikit-learn, matplotlib, and PostgreSQL for data processing/schema design and developed a Tableau dashboard connected to the database. Cut the project time in half using this method and helped scientists replace (multiple) excel files.
  • Enhanced nanoparticle targeting by applying different statistical models in Design of Experiments (DOE). Utilized matplotlib, scikit- learn, pyDOE, and PyTorch for regression and normalization to identify the most effective formulation. Achieved a 5-fold improvement in lead product efficacy.

Research Associate at Guide Therapeutics x Beam Therapeutics

July 2020 – January 2022 Atlanta, GA

  • Guide Therapeutics was a seed stage startup focused on in-vivo barcoding of mRNA in order to determine highly effective lipid nano particles. This company was bought by Beam Therapeutics in February 2021.
  • Built a high-throughput genomic analysis pipeline using Nextflow, orchestrated via Lambda and S3 triggers. Leveraged tools such as Samtools, Bowtie, Novoalign, and Jellyfish for efficient read alignment and transcriptomic analysis. Cut weekly experiment analysis time by over 50% and improved accuracy in identifying high-efficacy novel lipids, directly supporting GuideTx’s core technology platform.
  • Enabled successful transfer of high throughput lipid nanoparticle screening platform from GuideTx to BeamTx through acquisition.

Clinical Research Associate at Emory University

August 2018 – July 2020 Atlanta, GA

  • Emory University is an academic institution in Atlanta, GA known for their world renowned healthcare system and their cutting edge medical research.
  • Analysis and data pipeline building for transplant immunology. Utilized R and Python for analyzing high-dimensional and spatial transcriptomics in transplant immunology, utilizing dimensionality reduction tools (Seurat, t-SNE, UMAP) and ML models (Random Forests, KNN, K-Means, DBSCAN) within Keras and PyTorch for advanced immune cell biodistribution analysis.