About the job
About Crunchyroll
Crunchyroll is a fan-founded company dedicated to bringing the artistry and culture of anime to a vibrant community. Serving over 100 million anime and manga enthusiasts in more than 200 countries, we connect fans with the stories and characters they love. Our offerings include streaming video, theatrical releases, games, merchandise, events, and more, all powered by the anime content that we cherish.
Join us in shaping the future of anime!
About the Role
As part of Crunchyroll's Platform Development organization, you will help power the infrastructure that delivers anime to millions of fans globally. We are looking for a Staff Software Engineer to join our dynamic team in Los Angeles.
In this pivotal role, you will lead the design and evolution of core platform services that fuel Crunchyroll's global ecosystem. Your responsibilities will include enhancing authentication and security, developing notification services, and managing ML inference runtimes. Your contributions will lay the groundwork for engineering teams to create reliable, secure, and intelligent experiences at scale.
You will spearhead architectural initiatives, set technical direction, and guarantee system scalability, performance, and resilience in distributed environments. Collaborating closely with ML, data science, and engineering teams, you will refine platform capabilities that facilitate the deployment and operation of models in production, ensuring they adhere to the reliability and efficiency standards expected of a global streaming service.
In this position, you will report directly to the Engineering Manager of the Platform.
Core Areas of Responsibility
- Architect, build, and sustain ML inference runtimes for multi-model serving, autoscaling, and GPU/TPU utilization.
- Optimize inference pipelines and platform services for enhanced performance, reliability, and scalability.
- Oversee the deployment, operationalization, and maintenance of ML workloads in conjunction with ML and data science teams.
- Develop and maintain essential platform services, including authentication, security, and notifications.
- Ensure seamless integration with platform infrastructure, CI/CD pipelines, and observability systems.
- Design scalable system architectures and guide cross-team design alignment.
- Create benchmarking, validation, and monitoring tools to track and uphold system performance.
- Champion security, compliance, and engineering best practices across platform and ML services.
- Mentor and guide engineering colleagues, fostering a culture of technical excellence and consistency.

