Staff Software Engineer, ML Infra & Distributed Systems

Staff Software Engineer on ML Infrastructure team at Tubi, building scalable, low-latency ML inference platforms for recommendations, search, and content understanding. Responsibilities include designing distributed systems in Scala, building reusable components, partnering with ML engineers, optimizing latency/cost, mentoring, and defining long-term architecture. Requires experience with distributed systems, AWS, microservices, SQL/NoSQL, Kafka, Docker/Kubernetes, and incident response. Bonus:

Experience designing and building scalable distributed systems in Scala, Java, Python, Go, C++; strong AWS experience; building online microservices at scale with low latency; SQL (Postgres) and NoSQL (Cassandra), message brokers (Kafka), caches (Redis); containerization (Docker, Kubernetes); led major incident response. Bonus: familiarity with ML inference engines, vector stores, feature stores; understanding of ML training pipelines, recommender systems, search, autocomplete, ads ML; previous