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.

• 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.

• Led team of 3 - UX designer, data scientist and data entry / annotators.
• Designed and developed entire responsive React webapp for PickupMVP.com
• Leveraged Flutter inappwebview with addJavaScriptHandler to provide native functionality like DeepLinks, Push Notifications, and connect to other installed applications for authentication.
• Optimized Redux to share context across decoupled components with minimal redraws

• 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.