AIML - Software Engineer, MIND

SummaryPosted: Mar 1, 2024Weekly Hours: 40 Role Number:200518955The Machine Intelligence Neural Design (MIND) team at AIML is actively looking for a highly motivated Software Engineer to contribute and build Apple's future machine learning experiences. Our mission is to innovate and build differentiating experiences through research and development in machine learning. Applications of our work include interactive technologies, perception, and spatial computing experiences. The successful candidate will demonstrate deep knowledge of software engineering, applied machine learning, large language models (LLMs), interaction techniques, and deep expertise in the Apple ecosystem. A background in research, human-computer interaction, and experience prototyping is a plus. Our team builds technology that will drive effortless user experiences, and therefore we are seeking candidates who are creative and innovative. Tenacity and the passion to learn are skills we value in our team, and if you want to influence the future of Apple products, we want to talk to you.Key QualificationsKey QualificationsProficient in Python, proven understanding of C++DescriptionDescription- Implement features in our brand-new simulation engine for next-gen accelerators - Write unit and system integration tests to ensure functional correctness and to reduce performance regressions - Benchmark and diagnose performance bottlenecks of deep learning models - Work with HW Arch teams to co-design solutions that further improve performance and power of neural workloads - Work with a variety of partners from all parts of the stack from Apps to Compilation, HW Arch, and Silicon ValidationEducation & ExperienceEducation & ExperienceBachelor's, Master's, or PhD in Computer Science or a related field Additional RequirementsAdditional Requirements- Strong communicator with ability to analyze sophisticated and ambiguous problems- Disciplined programming abilities with a strong attention to detail- Experience with backend compilation, HW/SW co-design, and/or performance optimization- Deep understanding of computer systems and the interactions between HW and SW- Familiarity with at least one deep learning framework (e.g., PyTorch, Keras, TensorFlow)- Familiarity with ML model compression techniques (e.g., quantization, pruning) and their mapping to microarchitecture- Debugging model conversion from a high-level framework to a target device for correctness and performance issues