ML
SkylarkOS: Real-Time Perception on a Jetson
A ROS2-based autonomous UAV perception stack — detection, tracking, identity, and pose running concurrently on a Jetson Orin Nano with an 11ms camera-to-setpoint latency budget.
Machine Learning Engineer
Available for WorkMachine Learning Engineer building C++/ROS2 real-time perception systems, edge AI deployment pipelines, and cloud-based ML experimentation infrastructure. Experienced optimizing low-latency inference, benchmarking model performance, and deploying computer vision workloads on NVIDIA Jetson hardware.
1+
YEARS
3
PROJECTS
15+
TOOLS & FRAMEWORKS
ML
A ROS2-based autonomous UAV perception stack — detection, tracking, identity, and pose running concurrently on a Jetson Orin Nano with an 11ms camera-to-setpoint latency budget.
ML
A MobileNetV2-SSD object detector built from scratch in TensorFlow, including the data pipeline, training loop, and spot-instance training infrastructure, deployed for real-time inference on Jetson edge hardware.
ML
A from-scratch TensorFlow implementation of Faster R-CNN, covering the shared backbone, region proposal network, RoI pooling, and the joint classification and regression head.
ML2026.04.2415 MIN
Model choices, precision tradeoffs, and the latency budget behind a multi-model perception stack running at 62fps on an autonomous drone
BACKEND2026.04.1016 MIN
How to train a 200-epoch object detection model on AWS spot instances for a fraction of on-demand cost — with automatic recovery when they get reclaimed