OnDevice Application Engineer - Manufacturing Systems and Infrastructure
Apple · Operations and Supply Chain
Apply ↗Skills
["CI/CD""Computer Vision""Generative AI""LLMs""Machine Learning""Objective-C""Python""RAG""Swift"]Technology stack
{"programming_languages": ["Python""Swift""Objective-C"]"frameworks": []"databases": []"cloud": []"infrastructure": ["CI/CD"]"data_tools": []"ai_ml": ["LLMs""Machine Learning""Computer Vision""Generative AI""RAG"]"other_tools": []}Description
As an OnDevice Application Engineer with the MSI team, you will serve as a subject-matter expert in native application development and on-device AI/ML integration. You will drive the architecture and development of high-performance native applications that power our OnDevice ecosystems — leveraging AI, the iOS frameworks, and Apple-specific APIs to support manufacturing infrastructure at scale. You will own complex, cross-functional initiatives end-to-end — from architecture and design through delivery and post-deployment reliability — while setting engineering standards and best practices for the team.
Requirements
["6+ years of hands-on experience in native application development with a strong focus on iOS and macOS platforms", "Expert-level proficiency in Swift and strong working knowledge of Objective-C, with demonstrated capability of leveraging Generative AI coding assistants (e.g., GitHub Copilot, Cursor) to accelerate feature development, code refactoring, and daily programming tasks", "Deep expertise in the Apple ecosystem with a proven track record of seamlessly integrating AI/ML models into production-grade applications", "Deep expertise in Apple frameworks — UIKit, SwiftUI, Combine, and Foundation — with specialised, hands-on knowledge of Apple’s machine learning stack: Core ML, Vision, Create ML, and Metal for hardware-accelerated edge inference", "Deep understanding of multi-threaded system design — GCD, async/await, actors, and thread-safety patterns — critical for running computationally intensive AI models locally without degrading the end-user application experience", "Proven ability to define and enforce mobile/desktop performance optimisation strategies covering memory, battery, GPU utilisation, and application launch time in the context of on-device AI workloads", "Preferred: Excellent communication skills - ability to articulate technical trade-offs clearly to both engineering teams and non-technical manufacturing stakeholders", "Preferred: Practical experience using AI-centric scripting languages (Python) alongside GenAI tools to automate data handling, synthesise test data and streamline model integration workflows", "Preferred: Experience integrating applications with REST/GraphQL web services, event-driven backends and both cloud-based and local AI inference engines - including LLM APIs and computer vision model integration", "Preferred: Solid command of release engineering and SDLC best practices, with experience using AI tools to optimise CI/CD pipelines and manage the complex nuances of deploying machine learning model updates alongside application binaries", "Preferred: Demonstrated experience in quality engineering - unit, UI and performance testing - leveraging Generative AI to automate test script creation, generate edge-case scenarios and validate AI model accuracy", "Preferred: Familiarity with AI-powered quality and visual testing tools integrated into daily testing workflows to ensure application stability and reduce manual review time", "Preferred: Experience in manufacturing, factory automation or industrial IoT software domains", "Preferred: Published apps on the App Store or a strong portfolio demonstrating technical depth in on-device AI and native platform development"]
Roles & responsibilities
[]
About