Software Engineer, ML Performance

Overview

Technical role bridging ML research and real-time deployment for robotics.

Ideal candidate has 3+ years deploying ML models on embedded platforms and strong CUDA experience.

Locations

• United States

Requirements

• Bachelor's degree required
• 3+ years experience deploying ML models
• 2+ years experience with CUDA and TensorRT
• Proficient in Python and C++
• Experience with NVIDIA Jetson
• Familiarity with model conversion workflows

Responsibilities

• Own ML model deployment lifecycle
• Optimize models for Jetson platforms
• Develop CUDA kernels for inference
• Profile ML workloads
• Identify compute bottlenecks
• Design model compression strategies
• Manage memory and concurrency
• Collaborate with QA teams