Do you want to make Siri and Apple products smarter for our users? Here in the Machine Learning Platform Technology & Infrastructure group we build groundbreaking technology for algorithmic search, machine learning, natural language processing, and artificial intelligence. The features we build are redefining how hundreds of millions of people use their computers and mobile devices to search and find what they are looking for. Siri’s universal search engine powers search features across a variety of Apple products, including Siri, Spotlight, Safari, Messages, Lookup, and more. As part of this group, you will work with one of the most exciting high performance computing environments on Apple’s search product, with petabytes of data, millions of queries per second, and have an opportunity to imagine and build products that delight our customers every single day.

In this role working on search you will work at the intersection between quality and performance, optimizing the high performance components that serve our indexes for large amounts of traffic, working on retrieval infrastructure to improve relevance for users inside the constraints that come with a high throughput index serving infrastructure, designing and implementing retrieval augmented generation that is fed by our search systems. The typical tasks encompass: * Designing features and systems that enable to perform retrieval on large token and embeddings-based indexes * Optimizing throughput of the queries, analyzing how to let ranking engineers improve the relevance within the latency and budget envelope * Streamlining onboarding and experimentation experience to our search systems to empower other teams to more efficiently use our components and iterate faster on their relevance improvements * Improving data structures and algorithms to reduce the cost of serving large indexes