Description
We're seeking a Machine Learning Integration Engineer to join our team for building seamless, efficient deployment pipelines for ML models across multiple Apple products. You'll work at the intersection of machine learning, systems engineering, and product development, ensuring our ML capabilities reach users through reliable, performant integrations.
Your key responsibilities in this role are:
- Design, implement, and maintain efficient ML model deployment pipelines across Apple products for our real-time scene-understanding algorithms.
- Optimize model performance for diverse hardware configurations across Apple Silicon.
- Build and maintain MLOps infrastructure supporting continuous integration and deployment.
- Collaborate with ML researchers to transition models from experimentation to production.
- Work fluently across multiple codebases including Swift, Objective-C, Python, C++.
- Develop APIs and SDKs that enable seamless ML model consumption across teams.
- Ensure consistent model behavior and performance across different platforms and devices.
- Profile and optimize model inference performance, memory usage, and battery efficiency.
- Implement robust error handling, fallback mechanisms, and monitoring systems.
- Collaborate with QA teams to establish testing strategies for ML-integrated features.
- Develop apps / dashboards (as required) to enable debugging/triage/live-assessment from QA teams.