ML Runtime Optimization Engineer

About the role

Applied Intuition is seeking an experienced software engineer to lead the optimization of machine‑learning models for production‑grade embedded runtimes. You will work across the full ML stack, from model design to deployment on a range of compute platforms used in autonomous driving systems.

Key responsibilities

• Drive ML performance optimization on multiple technologies for on‑road and off‑road ADAS/AD stacks targeting deployment on a variety of embedded compute platforms.
• Develop compute usage strategies to improve efficiency and latency of model inference on customer‑selected boards.
• Implement model pruning and quantization techniques for memory‑constrained devices.
• Collaborate with ML engineers and software developers to identify and refine efficient model architectures.
• Set up profiling methodologies to locate performance bottlenecks on target embedded platforms.

Required profile

• Bachelor’s degree in Electrical Engineering, Computer Science, Mathematics, Physics or a related field.
• 3+ years of experience with ML accelerators, GPU, CPU, SoC architecture and micro‑architecture.
• Strong software development background focused on embedded programming.

Required skills

• Experience with deep learning frameworks such as PyTorch, JAX, ONNX.
• Proficiency with inference runtimes including TensorRT, CUDA, XLA, Triton.
• Model pruning and quantization for memory‑constrained platforms.
• Profiling and performance optimization on embedded compute boards.

What we offer

• Competitive compensation and benefits.
• Hybrid work model with primary onsite presence in Sunnyvale.
• Opportunity to work on cutting‑edge self‑driving technology.