Senior / Staff ML Systems Engineer – Framework Integration
Core
Own the path from a model in a ML framework down to running fast on a target hardware, working at all levels of the software stack from quantization to compiler abstractions to final target code generation.
Role type
Staff ML Systems Engineer (Framework Integration & Compiler)
Builds
Deployment Platform for running models on disruptive edge hardware
Domain
AI/ML, Embedded Systems, Compiler Technology, Edge Computing
Deliverable
production ML models
Required skills
C/C++, Python, AI/ML frameworks, accelerator toolchains (NPUs/DSPs/GPUs), compiler design, runtime optimization, memory model management, technical leadership, mentorship
Preferred skills
PyTorch, ONNX, TensorFlow, hardware architecture collaboration, automotive/medical/industrial deployment experience
Technologies
PyTorch, ONNX, TensorFlow, C/C++, Python
Responsibilities
Own the end-to-end path from ML framework models to fast code on target hardware; Bring up reference models using Roofline's SDK and fix root-cause issues; Set technical direction across ML, compiler, runtime, and architecture teams; Turn findings into products to improve the SDK and support latest models; Interact with the open-source ML community; Mentor junior engineers and maintain technical culture
