• Implemented OpenAI agent to recommend content types, fields and relationships, return both reasoning and a structure JSON schema.
• Wrote tools to parse Objects spreadsheet and auto-generate React forms, Django models, views, URLs, serializers, and Swagger documentation.
• Wrote tools to parse Permissions spreadsheet and produce strict TypeScript definitions and robust access control functions.
• Expanded demo Django server with AllAuth and Twilio SMS integration.
• Created a ReactJS application to render navigation of entire schema with CRUD functionality conditional to configured permissions.
• Developed a NodeJS fake data generator using the faker library to insert and update infinite rows of realistic data tailored to field types.
• Authored a comprehensive Cypress.io test suite to automate end-to-end testing of all CRUD operations against the API.
• Built a robust CI/CD pipeline with GitHub Actions to automate release tagging, changelog generation, and streamlined deployments to Cloud Run and Cloud Storage Bucket.

• Annotated data set and trained YOLOv4 model for detecting 6 classes across different sports.
• Designed all business logic for tracking the clip's subject, athlete, and ball.
• Wrote video annotation tool for ongoing additions to data set.
• Built video effect automation with ffmpeg and scikit using YOLO and DeepSort.
• Streamlined complete deployment pipeline with Bash and gcloud to GCP.
• Extended Track Authority Music platform and API to connect all rating and reward services.

• Maintained Django APIs and MySQL database powering mobile app and admin portal.
• Wrote efficient Stored Procedures to replace Django ORM queries and unnecessary serializers.
• Optimized SQL queries and aggregation endpoints for analytics dashboard, doubling data output while maintaining speed and adding search filters.
• Wrote k6 tests to benchmark API performance across all environments.
• Enhanced PDF generator for canvasser routes and instructions.

AI Annotation Interface & APIs

• Created several custom Node-Red modules for configuring cameras and communication with onprem tools and cloud APIs.
• Implemented secure API endpoints for detecting motion using Structural Similarity and manipulating images by any of 19 OpenCV filters and all possible validated arguments.
• Built entire front-end annotation tool with zooming, version controls, infinite tag nesting capabilities.
• TypeScripted client-side demo builder to double as a unit testing for reloading randomized training tags and showcase functionality.
• Introduce tools to calculate the range of tag type dimensions to help QA find tagging anomalies.
• Wrote ExpressJS server for managing photo training data and augmented variations hosted on any storage system via Minio.

Workstation Guidance

• Developed workstation guidance system for factories to configure assembly instructions with QA and computer vision assistance, including all Docker files to network and containerize full stack: Express, Mongo, Node-Red, React WebApp.
• Wrote cookie & CSRF secured backend to store and validate both manager configurations, and worker assembly runs with great detail and security protocols.
• Build React interface with modern Context implementation and MUI Styled components.
• Built bi-directional persistent WebSocket connection for constant communication with Node-Red service and FlexibleVision as a whole.

• Wrote Django API, CMS, and CD pipeline to GCP
• Built GCP server with load balancers for API on Cloud Run with Cloud SQL, and for the web app in a HTTPS Cloud Bucket
• Integrated various social APIs using OAuth2 for authentication and syncing music playlists

• Built tool to test performance of different OpenAI API use cases, by comparing Embeddings, Completions, and Assistants each with different prompt structures.
• Created front end visualization table to filter and compare results.
• Wrote python scripts to build PKL file of embeddings from data sets of product descriptions and metadata, provided as CSV, JSON, HTML or raw text.
• Created result schema to map AI recommendations back to prompt speeds, configurations and embedded vector stores in order to fine tune results with confidence.

• Designed advanced penetration tests in order to generate training data and formulate IoC Patterns based on signatures seen in logs.
• Developed interface with a streamlined workflow to control ingestion, triage alerts and fine tune inference engine analysis. Forked from OpenCTI.
• Implemented deduplication of Email data by maintaining checksum IDs on EML parts and it's whole.
• Wrote Ingestion system to run log / email imports at any interval with encrypted authentication credentials, with configurations for pre-tagging data and controlling retention and shareability policies.
• Drafted all system Data Flow Diagrams for both architectural documentation and patent application.
• Configured Docker containers and managed end-to-end DevOps processes on GCP, including CI/CD pipeline automation for seamless deployment and scalability.
• Built Puppeteer crawler to ingest client websites and learn URL patterns & HTML semantics for additional training data.