Machine Learning Engineer, Ops

We are seeking an MLOps Engineer to build and scale inference infrastructure for generative audio models (TTS, voice conversion, ASR). Responsibilities include designing and deploying low-latency, reliable, scalable systems for streaming and batch inference; implementing high-performance inference engines; Kubernetes orchestration and autoscaling; CI/CD pipelines; observability; collaborating with research; and optimizing GPU-accelerated inference. Required: deep understanding of audio model architectures, hands-on Kubernetes, MLOps, CI/CD automation, experience with Python or Go, and GPU inference profiling. Familiarity with Triton or vLLM-Omni is a plus.