Cantina is looking for a Machine Learning Engineer to bridge the gap between AI research and production systems, focusing on building and maintaining the infrastructure for their video-first AI products.
Requirements
- 2+ years of ML engineering, data engineering, or relevant experience
- Experience building video/audio data processing pipelines using serverless GPU infrastructure like Runpod or similar providers.
- Familiarity with machine learning and deep learning frameworks (PyTorch, TensorFlow)
- Experience deploying ML models to inference platforms like Baseten or similar providers
- Track record of adapting to new domains and using ML to improve products
- Experience with AWS services (S3, DynamoDB) and containerization tools like Docker and Kubernetes
- Passionate about video AI, multimodal models, or conversational AI
Responsibilities
- 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.
Other
- Collaborate across teams – Work closely with research teams to understand model requirements and with product teams to ensure AI capabilities align with user needs.
