Description
ElastixAI, an early-stage startup building a next-generation AI inference platform, is hiring a Machine Learning Engineer in Seattle, Washington for a hybrid role requiring three days per week in office. The engineer will design and develop core ML platform components including model deployment, optimization pipelines, benchmarking, and simulation workflows, while collaborating with systems and cloud engineers to improve inference performance across hardware targets. The role requires an advanced degree, 3+ years of ML R&D and deployment experience, programming proficiency in Python or C++, familiarity with ML frameworks such as PyTorch, TensorFlow, or JAX, and strong software engineering and collaboration skills. Preferred experience includes generative models, performance optimization, research leadership, cloud platforms, and container/orchestration tools.
