About this role
As an ML Engineer, Audio at Sandbar you will develop, evaluate, and deploy STT/TTS models across cloud and resource-constrained on-device settings, optimize inference pipelines for latency, reliability, and concurrency, and collaborate with ML/AI engineers, infrastructure engineers, designers, and cofounders on the Stream conversational product.
Skills for this role
Machine LearningAudio/Voice ModelsSpeech-to-Text (STT)Text-to-Speech (TTS)On-device MLCloud MLInference PipelinesLatency OptimizationReliability EngineeringConcurrency ManagementModel EvaluationModel DeploymentHuman-in-the-loop SystemsAgentic SystemsHuman-Computer InteractionShipping ML-based Products