Machine Learning Engineer

We're looking for a Machine Learning Engineer who thrives at the intersection of cutting-edge AI and real-world deployment. You'll be the bridge between our AI research and production systems, building and maintaining the infrastructure that powers our video-first AI products. This is a generalist role where you'll split your time between deploying state-of-the-art models to production and engineering the data pipelines that feed them As a ML Engineer, you will: - Own model deployment end-to-end – Take our latest video AI models from research to production. Build robust inference endpoints, optimize performance, and ensure our models scale seamlessly across cloud infrastructure providers like Baseten. - Build production-grade inference pipelines – Design, deploy, and maintain ML services that handle real-time video processing. Debug complex issues, optimize latency, and ensure 99.9% uptime for our AI-powered features. - Engineer video data workflows – Build scalable preprocessing pipelines using serverless GPU infrastructure (RunPod, etc.) to transform raw video and audio data into model-ready formats. Handle everything from format conversion to feature extraction at scale. - Architect cloud-native ML systems – Leverage AWS services (S3, DynamoDB, Lambda, ECS) and Kubernetes clusters to build resilient, scalable data and inference infrastructure. Design systems that can handle terabytes of video data efficiently. - Automate data annotation at scale – Build and maintain labeling pipelines using AWS Ground Truth and Mechanical Turk. - Collaborate across teams – Work closely with research teams to understand model requirements and with product teams to ensure AI capabilities align with user needs.