Embedded ML Engineer: Real-Time On-Device AI

Intelliswift - An LTTS Company; Redmond; On-site; AUD 158,000 - 244,000; Full time

Job summary

Intelliswift - An LTTS Company is seeking an Embedded Machine Learning Engineer to deploy ML models on wearable, audio, and intelligent devices. The role emphasizes transitioning research models to production on resource-constrained hardware with a focus on latency, memory, and power efficiency.

The candidate will train and fine-tune models using PyTorch or TensorFlow and develop high-performance C/C++ software for on-device inference, working closely with researchers and engineers in a

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
• Experience deploying and optimizing ML models on embedded or resource-constrained devices.
• Hands-on experience with PyTorch or TensorFlow.

Responsibilities

• Collaborate with researchers and engineers to transition ML models from prototype to deployment.
• Train, fine-tune, and adapt deep learning models with deployment constraints in mind.
• Optimize models for on-device inference via quantization, pruning, distillation, and architecture optimization.
• Deploy, integrate, and profile ML models on embedded hardware platforms.
• Develop high-performance C/C++ software for inference pipelines and real-time systems.
• Analyze and resolve performance bottlenecks related to latency, memory, and power.
• Build tools and infrastructure that accelerate model evaluation and deployment workflows.
• Partner with cross-functional teams to integrate ML into embedded systems.
• Document technical solutions and contribute to best practices across engineering.
• Stay current with advancements in ML, embedded computing, and edge AI.

Skills

C/C++ development

Embedded hardware

Model deployment

PyTorch / TensorFlow

Education

Bachelor's degree in CS/CE/EE

Tools

PyTorch

TensorFlow

Job description

Intelliswift - An LTTS Company is seeking an Embedded Machine Learning Engineer to deploy ML models on wearable, audio, and intelligent devices. The role emphasizes transitioning research models to production on resource-constrained hardware with a focus on latency, memory, and power efficiency.

The candidate will train and fine-tune models using PyTorch or TensorFlow and develop high-performance C/C++ software for on-device inference, working closely with researchers and engineers in a