Description
As an engineer in this role, you will be primarily focused on developing APIs in coremltools to enable ML engineers to efficiently author/convert ML models to CoreML, including any feedback APIs to help them evaluate the CoreML programs. The conversion APIs also include optimizations to enable peak performance on Apple devices, such as quantization, compression, distillation, etc. The role requires a good understanding of ML modeling (architectures, training vs inference trade-offs, etc.), and a good understanding of designing Python APIs and packages.
We are building the first end-to-end developer experience for ML development that, by taking advantage of Apple’s vertical integration, allows developers to iterate on model authoring, optimization, transformation, execution, debugging, profiling and analysis. The core ml tools authoring and conversion APIs are the entry-point to the rest of the infrastructure stack.
Key responsibilities:
Develop APIs in coremltools for ML engineers to efficiently convert models from ML frontends (such as PyTorch, JAX) into CoreML’s model representation.
Develop APIs in coremltools for ML engineers to author/tailor programs to achieve peak performance on Apple devices (e.g., quantization, distillation, custom operations, etc.)
Develop APIs, and tools for ML engineers to evaluate and converted/authored programs.