Staff / Principal Machine Learning Engineer – Anywhere

Inworld is a research laboratory specialising in real-time voice models utilised in various AI applications across sectors such as health, fitness, and media. The engineer will be responsible for optimising model serving frameworks, implementing acceleration techniques, and handling distributed system scaling in high-performance environments. Candidates should possess expertise in inference optimisation, model acceleration, and scalable cloud platforms, with skills in C++, CUDA, and Python. Experience with Kubernetes, Ray, or multi-GPU inference is advantageous, alongside a strong background in computer science or related fields. Responsibilities include taking models from research to production, improving system reliability, and engaging in open-source projects to advance the field.