cantina - Machine Learning Intern

• Projects may focus on post-training and inference efficiency for video generation models, reward modeling and preference-based optimization, multimodal data systems, or scalable infrastructure for video model training. The primary focus will be your core project, with opportunities to contribute to applied or product-adjacent work where relevant. • What You’ll Work On • Depending on your project, you may: • Develop reward models to improve aesthetics, motion quality, temporal consistency, and prompt adherence • Study how base-model behavior affects post-training outcomes and use experimental findings to inform model development • Design rigorous evaluations and conduct large-scale experiments on generative video models • Build systems for ingesting, preprocessing, curating, and delivering large-scale video datasets • Develop distributed pipelines for dataset generation, deduplication, preprocessing, and repeated dataset refreshes • Improve the reliability, reproducibility, and efficiency of data and model-training workflows • Build tooling for video and multimodal data using technologies such as FFmpeg, PyAV, DALI, or OpenCV • Contribute to evaluation harnesses, model integrations, research tooling, or other product-adjacent projects related to your core work • Document and communicate your findings through research reports, internal presentations, demonstrations, and potential conference submissions • You may be a good fit if you • Are pursuing a bachelor’s or master’s degree in computer science, engineering, machine learning, or a related field • Have experience building data pipelines, ML infrastructure, or distributed systems through research, coursework, open-source contributions, or previous internships • Are familiar with tools such as Ray, PySpark, Airflow, Docker, Kubernetes, or equivalent technologies • Have worked with cloud storage or compute platforms such as AWS, Google Cloud, or Azure • Understand practical considerations around data throughput, storage layout, caching, monitoring, and failure recovery • Are proficient in Python and interested in building reliable systems for large-scale machine learning • Experience with video, image, audio, or other multimodal data is valuable. Publications at leading venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, or AAAI are a plus, but are not required. We care most about the quality of your thinking, the depth of your technical work, and your ability to learn quickly. • What You Can Expect • A defined project and named senior mentor before your first day • Weekly one-on-one meetings and clear project milestones • A meaningful compute allocation for your research