AI Annotation Interface & APIs

• Created custom Node-Red modules for configuring cameras and communication with on-prem tools and cloud APIs.
• Implemented API for motion detection using Structural Similarity, to expose 19 OpenCV filter options to training interface, to manage photo training data and find tagging anomalies.
• Built entire front-end annotation tool with zooming, version controls, infinite class nesting.

Workstation Guidance

• Developed workstation guidance system for factories to configure assembly instructions with QA and computer vision assistance, dockerized to deploy across a local network of factory computers.
• Built bi-directional persistent secure 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.
• Forked OpenCTI as interface to control ingestion, triage alerts and fine tune inference engine analysis.
• Wrote Ingestion system to run log / email imports at any interval with encryption in transit and at rest, supporting configs for data retention and shareability policies.
• Implemented deduplication and aggregation of Email data by maintaining checksum IDs on EML parts and its whole.
• Built Puppeteer crawler to ingest client websites and learn URL patterns & HTML semantics for additional training data and monitoring standards.
• Drafted all system Data Flow Diagrams for both architectural documentation and patent application.
• Wrote Docker containers and CI/CD pipeline from GitHub Actions to GCP.

• 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 dataset 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 dataset.
• 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.