Enabling streamlined decision making through improved data reporting efforts and supporting clinicians and internal staff as the primary Analytics Engineer within the Corporate Reporting team.

Key Responsibilites:

• - Spearhead the development and maintenance of dataflows to support multiple teams and staff in a cross-functional manner.
• - Take ownership of the development and design of data dashboards on multiple platforms used to both automate data retrieval process, as well as provide insight into ongoing performance.
• - Meet with teams in a cross-functional and collaborative manner to improve data reporting capabilities, and innovate in ways that reduce operational bottlenecks.
• - Conduct research and development of core KPI's and visuals that contribute to the optimization of business performance from both a financial and operational perspective.
• - Created documentation that clarified contractual obligations, restraints, technical processes, and key points-of-logic which was understood by staff at varying levels of management (including C-Suite/Executive).
  
  Primary Tools:
  • - Snowflake SQL
  • - Microsoft SQL Server
  • - Microsoft PowerBI, DAX
  • - Microsoft PowerApps
  • - Microsoft Excel

Sat within the core data team among software and energy engineers to develop data monitoring systems, improve overall data QA across the product vertical, and take lead on data stewardship activities to support an organization's mission in improving energy efficiency at the consumer level.

Key Responsibilites:

• - Increased data retrieval and manipulation efficiency by facilitating the integration of Django ORM to streamline database interactions
• - Assembled large, normalized data lakes by constructing data (ETL) pipelines capable of ingesting and transforming data from over 20+ disparate data sources using Python, Django, and S3
• - Collaborated with external vendors and product stakeholders to understand data capabilities and product scope, leading to the delivery of detailed feature proposals and product roadmaps
• - Architected a data platform for managing over 10000+ consumer-facing products for an eCommerce catalog sourced from multiple 3rd party resources
• - Utilized Python, Looker, and SQL to engineer data reporting systems for consistent dashboard and visualization delivery to communicate business insights and pipeline performance to stakeholders
• - Designed data visualizations and analyses to identify root cause of data issues leading to the improvement of data quality across a large consumer-facing eCommerce catalog
• - Engineered complex SQL queries to serve ad-hoc requests to enable product stakeholders in making data-driven decisions
  
  Primary Tools:
  • - Python (Jupyter, Pandas, Numpy, Django)
  • - PostgreSQL
  • - Docker
  • - Git
  • - Google Looker Studio

Took ownership in researching the feasibility of using computer vision models for quantifying treatment agents to streamline the workflow of biomedical resreachers.

Key Responsibilites:

• - Constructed end-to-end data pipelines using Python and Pandas to enhance preprocessing and ingestion rates capable of producing an image dataset of 1000+ images and reducing manual workload by 70%
• - Independently spearheaded the development of 3+ common classification machine learning models for comparison of performance and presentation at multiple scientific conferences
• - Mentored junior researchers in utilizing data visualization tools in order to scale collaborative research efforts
  
  Primary Tools:
  • - Python (Jupyter, Pandas, Numpy, OpenCV)
  • - MATLAB
  • - Google Colab
  • - Git

Contributed to ongoing cybersecurity research in understanding the processing and visualization of network packet data between cloud systems.

Key Responsibilites:

• - Utilized remote Amazon Web Service instances across the domestic United States to simulate remote connection chains on a secure network
• - Analyzed network packet information later used by machine learning classification models such as Random Forests and support vector machines
• - Conducted in-depth analysis of network data to identify connection chain lengths between secure shell connections
  
  Primary Tools:
  • - AWS
  • - Python (pandas, numpy, sci-kit-learn)
  • - Google Slides

Took lead in researching the stepping-stone component of a larger reserach initiative. The results of my work in contribution to the astute academic scholars lead to the early comparitive models of automated data categorization systems using machine learning and AI. This work was recognized for benchmark comparisons in early development models by several companies such as Amazon, OpenAI, and Meta.

Key Responsibilites:

• - Scaled internal data storage systems through the systemization of data maintainability and implementation of strict data usage guidelines
• - Conducted thorough investigations into the data quality, integrity, and relevancy across 10+ external data sources, ensuring reliable and accurate information is used for research purposes
• - Successfully programmed 5+ text classification machine learning models through Python, scikit-learn, and Tensorflow, allowing for publication of insights at multiple scientific conferences and AI research groups
• - Utilized Jupyter Notebooks and visualization libraries for data analysis to consistently deliver accurate and comprehensive research reports with insightful visualizations over the course of a strict 3-month deadline
  
  Primary Tools:
  • - Python (pandas, numpy, matplotlib)
  • - LaTeX
  • - Google Slides

This was my first professional work-experience that was coding-based. The outcome was research that explored the applications of low-cost sensors to be designed as wearable controllers for users with limited mobility.

Key Responsibilites:

• - Accomplished a first-authored research paper that describes the results of utilizing low-cost wearable sensors to explore technology capable of tracking human head movement
• - Utilized simple machine learning models to categorize head movement based on real-time data
• - Demonstrated the capability of microcontrollers accurately tracking and sending data to communicate with machine learning models
  
  Primary Tools:
  • - Arduino Nano
  • - Raspberry PI
  • - Python (pandas, scikit-learn, numpy)