On-Device ML Engineering Manager, Tools & Services

What you'll do

• Lead the team building frontend and backend web services for introspecting ML models and on-device execution.
• Manage the development of an on-device toolchain to gather and report low-level performance data.
• Improve the end-to-end workflow for model authoring, performance profiling, and iterative model improvement.
• Own the infrastructure for running ML inference across large fleets of devices to ensure reliable performance data.
• Associate low-level performance signals with high-level framework-level operations like PyTorch.
• Hire and guide the careers of ML, software, and tools engineers.
• Partner with cross-functional teams to advance on-device ML functionality and performance.

What we're looking for

• BS/MS/PhD in Computer Science or Electrical Engineering.
• Two or more years of strong and validated management experience.
• Knowledge of ML development workflows, including experience with at least one authoring framework like PyTorch.
• Experience delivering web services and developer-facing tools spanning frontend and backend.
• Solid programming skills in at least one of the following: Python, Swift, Objective-C, or C/C++.
• Track record of creating clean software architectures, intuitive designs, and high-performance extensible software.
• Excellent communication skills.
• Experience with on-device ML frameworks, performance profiling, or MLIR/LLVM compiler technologies (preferred).