Senior Machine Learning Engineer, Inference - USA

At Inworld AI, the Senior Machine Learning Engineer role is part of the ML Engineering team focused on real-time AI inference for consumer applications. The company develops proprietary speech models and serves large language models through modular APIs designed for high-volume, low-latency workloads. Their technology supports diverse sectors including healthcare, education, and media, powering experiences for major clients like NVIDIA and Microsoft Xbox.

This position involves optimizing inference systems, accelerating model performance, and managing large-scale distributed systems. The engineer will work hands-on with technologies such as CUDA, C++, Rust, and Kubernetes to enhance GPU utilization and ensure reliable multi-node inference. Responsibilities include taking models from research through containerization and production deployment, emphasizing performance, latency, and stability as core product features.

Ideal candidates are adaptable problem solvers who thrive in ambiguity and prioritize impactful engineering over theoretical work. The role requires deep technical understanding, experience with inference optimization techniques, and a proactive approach to questioning and improving system architectures. The company values in-person collaboration and offers relocation support for work at their Mountain View office.