ML Compiler Engineer - End-to-End Deployment for Embedded AI

Lindus Health; Sunnyvale (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Wayve is hiring a ML Compiler Engineer to own the end-to-end ML compilation pipeline for embedded and accelerator targets. You will design passes, integrate with NVIDIA TensorRT and Qualcomm QNN, and deliver deployable bundles meeting strict accuracy and latency requirements across architectures.

You will extend precision typing, work on graph decomposition, and collaborate with model teams to ensure compilability.

Qualifications

• Experience building ML compilation pipelines.
• Deep experience with quantisation or graph lowering.
• Proficiency in Python; C++ is a plus.
• Familiarity with multiple backends and vendor toolchains.

Responsibilities

• Own the ML compilation pipeline end-to-end for target platforms.
• Design and implement compiler passes with accuracy and latency gates.
• Extend precision typing and graph-splitting for new architectures.
• Partner with model and training teams on compilability.
• Build regression tests and benchmarks across releases.
• Set technical direction and mentor the team on compiler design.

Skills

ML compilation

Graph lowering

Python

C++

TensorRT

QNN

Multi-target

Debugging

Cross-functional

Mentoring

Tools

MLIR

ONNX

TensorRT

QNN

PyTorch

Job description

Wayve is hiring a ML Compiler Engineer to own the end-to-end ML compilation pipeline for embedded and accelerator targets. You will design passes, integrate with NVIDIA TensorRT and Qualcomm QNN, and deliver deployable bundles meeting strict accuracy and latency requirements across architectures.

You will extend precision typing, work on graph decomposition, and collaborate with model teams to ensure compilability.