ML Engineer, On-device Inference

Shrink frontier models to fit on edge hardware without sacrificing the accuracy our customers depend on.

What you'll do

• Quantize, prune, and distill large perception models for edge deployment
• Benchmark inference across TensorRT, ONNX Runtime, and custom runtimes
• Build automated model optimization and profiling pipelines
• Collaborate with research to design architecture-aware efficient models

What we look for

• 3+ years in ML model optimization or deployment
• Hands-on experience with TensorRT, ONNX, or TFLite
• Strong Python and C++ skills
• Understanding of neural network quantization and hardware accelerators