About this role
Are you interested in revolutionizing how hundreds of millions of people utilize their devices to access information? As an engineer on the team, you will bridge the gap between cutting-edge foundation models and the end user, helping guide the products and features that bring our generative AI technologies to life.
In this role, you will be the critical engineering link between backend machine learning and the final user interface. You will be responsible for designing and implementing intelligent user experiences that leverage Large Language Models (LLMs). To make these experiences fast, accurate, and context-aware, you will integrate with data and services from multiple providers, building the complex orchestration layer required for Retrieval-Augmented Generation (RAG). You will work closely with our platform team to define the infrastructure interfaces necessary for low-latency model serving and secure data handling. Because you bring strong product thinking to the room, you will also partner directly with Apple Design and client-side teams to ensure a great user experience, translating complex AI interactions into flawless, intuitive features across Siri, Spotlight, and Safari.
Minimum Qualifications
3+ years of industry related experience, working in collaborative environments
Experience with prompt engineering and prompt tuning techniques to tasks, conducting systematic evaluation and iteration based on quality and consistency metrics.
Opinionated product-sense and focus on the end user-experience
Excellent problem solving, critical thinking, and communication skills
Proficient in at least two programming languages such as: C/C++, Go, Python, Java
Understanding product requirements then translating them into engineering tasks
Bachelors in Computer Science or related field or 2 years of equivalent work experience
Preferred Qualifications
Prior experience in consumer facing product is desired
In-depth experience with server-side development and deployment
Advanced degree in CS