WebAI is hiring a Software Engineer MLX to optimize machine learning models for iOS deployment. Use expertise in C++, Python, hardware-aware programming, and Apple’s MLX and Metal frameworks to accelerate performance on mobile devices. Build efficient, on-device AI solutions.
Key Responsibilities:
Optimize and deploy machine learning models on iOS devices using MLX and Metal frameworks. Develop high-performance, hardware-aware code in C++ and/or Python, focusing on vectorization, multi-threading, and system optimization. Build and optimize custom Metal kernels and computational graphs for mobile acceleration. Deploy and fine-tune PyTorch models for efficient, on-device inference. Apply quantization, tensor fusion, and batching strategies to maximize model performance and minimize size. Collaborate with AI researchers and mobile teams to deliver scalable, production-ready solutions. Monitor and improve model performance across the iOS lifecycle to ensure efficiency and reliability.