Senior On-Device AI Inference Performance Engineer

OpenInfer is seeking a highly skilled engineer to join their team, focusing on performance optimization for on-device AI applications. The role involves enhancing the inference engine's efficiency and collaborating with engineers to improve overall system performance.

Responsibilities:

• Innovate on the inference optimization pipeline through algorithmic and system optimization
• Own end to end system characterization across a range of hardware
• Own the design and implementation of inference optimizations for AI workloads, targeting peak efficiency on diverse hardware
• Engage in performance benchmarking, profiling, and troubleshooting to improve execution across various hardware
• Work on cross-functional teams to design, implement, and test new features