Machine Learning Engineer, Performance Tooling

📋 Description

• Own the ML compilation pipeline end-to-end — from checkpoint to deployable bundle on NVIDIA
• Design and implement compiler passes with accuracy and latency gates, so bad compiles are caught
• Build compilation infrastructure that scales across platforms, model architectures, and SoCs —
• Partner with model and training teams on compilability; build regression and benchmarking to
• Set technical direction and raise the bar for compiler engineering across the team.

🎯 Requirements

• Built or owned significant parts of an ML compilation or graph-lowering pipeline.
• Deep experience with quantisation in compilation — precision typing, PTQ integration, debugging
• Strong Python; comfortable building and testing compiler infrastructure in production codebases.
• Proficiency with at least one of: MLIR, ONNX, TensorRT, Qualcomm QNN, PyTorch graph capture/export.
• Experience with multi-target compilation or graph partitioning across hardware backends.
• Ability to reason about correctness and performance trade-offs at each compiler stage.