$ cat work/timeline.log | tail -n 4

Work.

  1. Senior Machine Learning Engineer

    › TransferX

    Feb 2026 - present
    • ›Owned and designed the execution of TransferX's end-to-end ML and data platform from scratch, spanning student-data ingestion, ranking models, and production APIs for 600+ students.
    • ›Built a proprietary ranking model that matches each transfer student to universities and programs, trained on 10K+ noisy, real-world student records and served in under 50ms.
    • ›Leading a team of 3 engineers and designing the AI Transfer Planner, where a rules engine checks prerequisites and credits and a RAG-based LLM explains each roadmap.
    • ›Designed the PostgreSQL schema and built ETL pipelines on AWS Lambda for enrollment and credit tracking, designed to scale to 1M students in 2 years.
    --postgresql--etl--python--aws-lambda--ranking--rag

  2. AI Systems Integration Engineer

    › Alta Potentia LLC

    Mar 2025 - Nov 2025
    • ›Optimized real-time YOLOv8 object detection on NVIDIA Jetson using TensorRT quantization, achieving <100 ms inference latency and a 60% smaller model footprint while maintaining accuracy, cutting edge infrastructure cost 30% per device.
    • ›Built a data pipeline processing 500K+ video frames for model retraining and evaluation in coordination with clients, reducing manual review workload 16% in retail loss prevention.
    • ›Integrated edge-vision inference into production security systems across 20+ retail locations, connecting camera streams, detection services, and real-time alerting for enterprise retail clients.
    --yolov8--jetson--tensorrt--onnx--vision applications

  3. Machine Learning Engineer

    › OWL Autonomous Imaging

    Jan 2024 - May 2024
    • ›Built a dual-encoder thermal-RGB sensor fusion model for autonomous navigation, extending MGNet (originally monocular RGB) to 16-bit thermal images for panoptic segmentation and self-supervised monocular depth estimation; improved segmentation performance 20% over an RGB-only baseline and anchored OWL's 3D scene-understanding roadmap.
    • ›Shipped perception models into OWL's ADAS perception software on NVIDIA Jetson AGX Orin, integrated via ROS at 30 FPS on-device with Dockerized CI/CD builds.
    • ›Built real-time super-resolution and denoising for synchronized 16-bit thermal-RGB streams at 1280x800 / 30 FPS, incorporating intrinsic/extrinsic calibration and sensor alignment for on-vehicle edge deployment.
    • ›Built a multimodal data pipeline across 4,000+ hours of thermal, RGB, and LiDAR capture, projecting 2D pseudo-labels into 3D point clouds and improving detection mAP 15% through class balancing and data-quality controls.
    • ›Built a panoptic annotation tool over Detectron2 auto-labels with a parallax-aware overlay and YOLOv5-based label QA, cutting labeling time 40% across 50K+ frames and reducing third-party annotation spend.
    --detectron2--yolov5--thermal-rgb--panoptic--docker--lidar--jetson-orin--ros

  4. Machine Learning Engineer

    › WhiteHat Education Technology

    Jun 2020 - Aug 2021
    • ›Built robust unit testing frameworks (PyTest) for 300+ Python ML projects, drastically reducing production failures.
    • ›Deployed automated data drift detection (MLflow, Airflow) to ensure stable model performance across diverse datasets.
    • ›Analyzed marketing, sales, and student data, implementing algorithms that boosted lead conversion, revenue, customer retention and learner engagement.
    • ›Led a seven-person team to design data-driven A/B tests and predictive analytics workflows, significantly improving student success rates and overall program efficiency.
    --mlflow--airflow--team-lead--production-ml--founding-team