Embedded ML Inference Engineer (Real-Time On-Device)

Creospan Inc.; Redmond; On-site; AUD 172,000 - 229,000; Full time

Job summary

Creospan Inc. in Redmond WA is seeking a Software Engineer III to develop, optimize, and deploy ML models on embedded devices for AR/VR and wearable technologies. You will blend hands-on model training with strong C/C++ development and real-time inference optimization.

The role requires collaborating with researchers and hardware teams to boost model performance within tight latency, memory, and power limits while delivering robust, on-device deployment.

Qualifications

• Bachelor's degree in CS, CE, EE, or equivalent.
• Experience optimizing ML inference on embedded devices.
• Hands-on ML training with PyTorch or TensorFlow.
• At least 2 years of C/C++ experience.
• Experience profiling ML performance on target hardware.

Responsibilities

• Train, fine-tune, and adapt ML models using PyTorch or TensorFlow.
• Optimize models for embedded deployment using quantization and pruning.
• Port, integrate, profile, and debug ML inference on embedded hardware.
• Develop high-performance C/C++ code for real-time on-device inference.
• Collaborate with researchers and hardware teams to improve deployment efficiency.

Skills

C/C++

ML model training

PyTorch

TensorFlow

Embedded systems

Education

Bachelor's degree in CS/CE/EE or equivalent

Tools

ONNX Runtime

TFLite/LiteRT

DSP SDKs

Job description

Creospan Inc. in Redmond WA is seeking a Software Engineer III to develop, optimize, and deploy ML models on embedded devices for AR/VR and wearable technologies. You will blend hands-on model training with strong C/C++ development and real-time inference optimization.

The role requires collaborating with researchers and hardware teams to boost model performance within tight latency, memory, and power limits while delivering robust, on-device deployment.