About this role
Senior individual-contributor role owning design, deployment, and operation of SimpliSafe's Kubernetes-based ML platform for real-time computer vision inference and LLM/GenAI serving. Responsibilities include driving architecture decisions, improving throughput/latency/cost for inference, establishing model lifecycle and reliability practices, and mentoring engineers across the Cloud ML team.
Skills for this role
Machine LearningCloud ML infrastructureKubernetesRayKServeTritonvLLMKubeflowArgoAWSEKSS3IAMNetworkingKafkaKinesisFlinkContainerized deploymentsCI/CDInfrastructure-as-codeGPU-aware schedulingBatching strategiesAutoscalingMulti-model servingMulti-tenancyPythonGoC++RustLLM serving''Generative AI''Computer Vision''Video processing''Real-time Inf