Contract Embedded ML Engineer — Real-Time AR/VR Audio

EPITEC; Redmond; On-site; AUD 178,000 - 188,000; Full time

Job summary

Reality Labs is seeking a Contract ML Software Engineer to port and optimize models for embedded devices, balancing latency, memory, and power constraints. You will work with researchers to convert prototypes to real-time inference and implement C/C++ pipelines for production use.

The role emphasizes on-device ML optimization, quantization, and tool development, with experience in audio/AR/VR domains and cross-functional collaboration.

Qualifications

• BS degree in Computer Science, Computer Engineering, Electrical Engineering, or related field.
• Industry experience optimizing and running ML inference on embedded or resource-constrained devices.
• Experience training ML models using PyTorch, TensorFlow, or similar frameworks.
• 2+ years of industry experience with C/C++.
• Experience profiling and debugging performance issues across ML models and target hardware.
• Experience collaborating within cross-functional technical teams.

Responsibilities

• Transition ML models from research to real-time inference on embedded devices.
• Train, fine-tune, and adapt ML models considering latency, compute, memory, and power constraints.
• Optimize models for on-device inference using quantization, pruning, distillation, and architecture adjustments.
• Port, integrate, and profile ML models on embedded hardware including DSPs, NPUs, MCUs, and mobile SoCs.
• Identify and resolve performance bottlenecks across ML models and target hardware.
• Develop clean, high-performance C/C++ code for real-time inference pipelines.
• Build tools and infrastructure to evaluate model accuracy and performance on target hardware.

Skills

C/C++

PyTorch

TensorFlow

Embedded ML

Performance profiling

Cross-functional teamwork

Real-time inference

Education

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

Tools

ExecuTorch

TFLite/LiteRT

ONNX Runtime

NPU/DSP SDKs

Job description

Reality Labs is seeking a Contract ML Software Engineer to port and optimize models for embedded devices, balancing latency, memory, and power constraints. You will work with researchers to convert prototypes to real-time inference and implement C/C++ pipelines for production use.

The role emphasizes on-device ML optimization, quantization, and tool development, with experience in audio/AR/VR domains and cross-functional collaboration.