ML Software Engineer, On-Device Inference
Context
A client developing wearable and AR glasses technology needs audio intelligence features running on resource-constrained hardware. The 12-month onsite contract is based in Redmond, WA, with W2 pay and benefits.
What you'll do
- Deploy and optimize machine learning models for real-time inference on wearable devices
- Improve model performance within compute, memory, latency and power constraints
- Apply quantization, pruning, distillation and performance profiling to on-device models
- Collaborate with research scientists and hardware engineering teams
- Build audio intelligence technologies for AR glasses and wearables
Profile
- 2+ years of strong C/C++ programming experience
- Machine learning experience with PyTorch or TensorFlow
- Embedded ML and on-device inference optimization experience
- Experience with DSPs, NPUs, mobile SoCs or resource-constrained devices
- Bachelor's degree in computer science, computer engineering, electrical engineering or a related field, or equivalent experience