Senior / Staff ML Training Optimization Engineer
Core
Optimizing deep learning models for inference on embedded systems and onboard compute for autonomous trucks.
Role type
Staff ML Training Optimization Engineer
Builds
Optimized inference models for autonomous truck compute systems
Domain
Autonomous transportation / Physical AI / Embedded Systems
Deliverable
production ML models
Required skills
CUDA kernel development, model profiling (CPU/GPU), TensorRT, PyTorch, C++, Python, Rust, embedded platform integration
Preferred skills
Bazel build systems, model compilation/exporting, third-party package integration
Technologies
TensorRT, modelopt, PyTorch Profiler, NVIDIA Nsight, Nvidia Jetson, Nvidia Thor
Responsibilities
Collaborate with autonomy engineers to scale self-driving systems, expand model deployment pipelines to new GPUs/embedded systems, create and benchmark CUDA kernels, profile model runtime and memory to identify bottlenecks
Seniority
Staff, hands-on IC
