Software Engineer - LLM Workflows - Apps

Make a difference. As a Software Engineer specializing in LLM Workflows on the Apps Engineering team, you'll collaborate daily with machine learning researchers, application engineers, framework engineers, and product designers to work on advanced language models and task automation. Your work will span the entire development lifecycle, from defining data requirements and evaluation frameworks to deploying LLM workflows across tools and applications. This role requires expertise in prompt engineering, retrieval-augmented generation, and model fine-tuning to create intelligent, context-aware experiences., * Design and implement LLM integration for applications and tools, deploying language models across diverse environments.

• Develop prompt engineering strategies and RAG systems to enable context-aware AI capabilities.
• Build evaluation frameworks and data collection pipelines to measure and improve LLM performance.
• Work cross-functionally with ML researchers, app engineers, and framework teams across Apple to prototype and validate AI-driven features.
• Implement fine-tuning workflows to adapt foundation models for specific domains and tasks.
• Optimize LLM inference performance for deployment on macOS and iOS devices, ensuring responsive user experiences.Contribute to the full feature development lifecycle from concept through launch, iterating based on evaluation metrics and user feedback.

Do you have experience in macOS?, Do you have a Master's degree?, * Experience fine-tuning Large Language Models for specific domains or tasks, alongside integrating LLMs and deploying fine-tuned adapters.

• Experience developing software applications using Python, Swift, or C++.
• Experience with REST APIs, JSON, and working with LLM services (e.g., OpenAI APIs).
• Experience building data collection and evaluation pipelines for machine learning systems., * BS/MS in Computer Science, Machine Learning, or related technical field, or 3 years of equivalent work experience.
• Experience with prompt engineering and optimization techniques for LLMs.
• Experience implementing retrieval-augmented generation (RAG) systems.
• Experience developing agentic workflows and orchestration systems.
• Experience with local model deployment and on-device LLM inference.
• Experience with Apple's Foundation Model framework or similar ML frameworks.
• Experience collaborating with framework engineers to optimize ML infrastructure.Experience working with creators, audio/video production, or creative software applications.