EVONA · 10 months ago
Machine Learning Engineer
EVONA is a venture-backed startup developing next-generation autonomous systems for defense and industry. They are seeking a Machine Learning Engineer to lead model deployment on low-cost embedded hardware, working on real-time computer vision and optimizing deep learning models for resource-constrained platforms.
Responsibilities
Design and train deep learning models for real-time computer vision
Optimize performance via quantization, pruning, and knowledge distillation
Deploy models on platforms like Jetson, Qualcomm, ARM Cortex, and ASICs
Contribute to SLAM, object detection, tracking, and sensor fusion pipelines
Write robust code in Python and C++, using TensorFlow, PyTorch, and ONNX
Collaborate closely across engineering teams to integrate ML into production
Qualification
Required
5+ years in ML/deep learning with a strong CV/compression focus
Hands-on with deployment on embedded hardware or edge devices
Fluency in Python, C++, and ML deployment frameworks (TensorRT, ONNX)
Background in optimizing models for latency, power, and memory footprint
Preferred
CUDA/OpenCL
robotics (ROS)
SLAM
multi-sensor fusion
Benefits
Full health/dental/vision
401(k)
Flexible PTO