Staff Software Engineer, AI Runtime Systems

Crunchyroll • Los Angeles, CA

29d • Hybrid

About The Position

Crunchyroll's Platform Development organization powers the infrastructure that delivers anime at scale to millions of fans worldwide. We are seeking a Staff Software Engineer to join our team in Los Angeles. In this role you will drive the design and evolution of core platform services that power Crunchyroll's global ecosystem. Your work will span authentication and security enhancements, notification services, and ML inference runtimes, forming the foundation that enables engineering teams to build reliable, secure, and intelligent experiences at scale. You will lead architectural initiatives, define technical direction, and ensure system scalability, performance, and resilience across distributed environments. Partnering closely with ML, data science, and engineering teams, you will shape the platform capabilities that support deploying and operating models in production, ensuring they meet the reliability and efficiency standards required for a global streaming service. In the role of Staff Software Engineer, you will report to the Engineering Manager, Platform. We are a dedicated Platform Development team building foundational services that enable engineering teams to deliver features faster and more reliably. Our mission is to create scalable, reusable, and high-quality systems across Crunchyroll, including core services, authentication/security enhancements, notifications, and ML inference runtimes. We leverage cloud-based microservices architectures and best practices to deliver reliable, maintainable, and high-performance services for Crunchyroll's global audience. Crunchyroll is the world's largest destination for anime and manga, boasting a global community of more than 25 million registered users and over 1 million subscribers. Fans connect through the most complete anime library including "Naruto Shippuden," "Attack on Titan," and "Dragon Ball Super," events such as Crunchyroll Movie Nights, Crunchyroll News, and can purchase related merchandise through its online store. Through its app on game consoles, set-top boxes, mobile devices and more, Crunchyroll delivers content from leading media producers directly to viewers translated professionally in multiple languages. The service is available for free or through a premium offering that allows users to watch ad-free with access to simulcasts-top series available immediately after Japanese broadcast.

Requirements

• 12+ years of backend software engineering experience, with a track record of leading complex projects end-to-end.
• Hands-on experience building and optimizing AI/ML inference runtimes (e.g., KServe, TorchServe, TensorRT, Triton) and integrating with CI/CD and MLOps pipelines (e.g., SageMaker, Kubeflow, BentoML).
• Expertise in JavaScript/TypeScript, with additional experience in Golang or Kotlin.
• Experience with containers, orchestration (Kubernetes/ECS), cloud platforms (AWS preferred), and distributed systems.
• Experience with performance profiling, model optimization, GPU acceleration, and designing inference workloads to meet latency/throughput SLAs.
• Experienced in building scalable APIs (REST/gRPC), caching strategies, and high-performance systems, including relational and NoSQL databases.
• Familiar with monitoring, observability tools, security, and compliance best practices in production ML/AI services.
• Proven ability to collaborate with ML/AI teams, bridge research and production, and mentor peers.
• Strong problem-solving, communication, and engineering best practices, with attention to detail and quality.
• Bachelor's degree in Computer Science, Engineering, or a related field-or equivalent practical experience.

Responsibilities

• Architect, build, and maintain ML inference runtimes for multi-model serving, autoscaling, and GPU/TPU utilization.
• Optimize inference pipelines and platform services for performance, reliability, and scalability.
• Lead deployment, operationalization, and maintenance of ML workloads in collaboration with ML and data science teams.
• Shape and maintain core platform services, including authentication, security, and notifications.
• Ensure seamless integration with platform infrastructure, CI/CD pipelines, and observability systems.
• Define scalable system architectures and guide cross-team design alignment.
• Develop benchmarking, validation, and monitoring tools to measure and maintain system performance.
• Promote security, compliance, and engineering best practices across platform and ML services.
• Mentor and influence engineering peers, fostering technical excellence and consistent standards.

Benefits

• Receive a great compensation package including salary plus performance bonus earning potential, paid annually.
• Flexible time off policies allow you to take the time you need to be your whole self.
• Generous medical, dental, vision, STD, LTD, and life insurance
• Health Saving Account HSA program
• Health care and dependent care FSA
• 401(k) plan, with employer match
• Employer paid commuter benefit
• Support program for new parents
• Pet insurance and some of our offices are pet friendly!

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Industry: Broadcasting and Content Providers
• Number of Employees: 101-250 employees