About this role
Design, build, and deploy production-grade ML systems with end-to-end ownership of the model lifecycle, focusing on audio data and natural speech interaction. Collaborate with cross-functional teams and customers to develop LLM and audio ML applications, real-time inference, and production monitoring.
Skills for this role
PythonTypeScriptPyTorchTensorFlowAWSAmazon S3FastAPIOpenAI APIBasetenLiteLLMLiveKitPostgreSQLRedisAudio MLNatural speech interactionReal-time inferenceModel monitoringData pipeline designFeature engineeringModel deploymentML systems architectureModel trainingModel evaluationCommunication