Staff Software Engineer, ML Infra & Distributed Systems
Core
Build world-class machine learning inference platforms powering personalized recommendations, search, and content understanding for Tubi's streaming service.
Role type
Staff Software Engineer (ML Infrastructure & Distributed Systems)
Builds
Low-latency ML model serving systems, inference engines, feature stores, vector stores, and experimentation engines.
Domain
Streaming media, Machine Learning Infrastructure, Distributed Systems
Deliverable
production ML models
Required skills
Distributed systems design, Scala, AWS, Online microservices, SQL/NoSQL databases, Message brokers, Containerization, Incident management, System architecture
Preferred skills
ML inference engines (TorchServe, Triton, vLLM), Vector stores, Feature stores, ML model training pipelines, Recommender systems, Search, Akka/Erlang/Elixir/Go, A/B testing analysis
Technologies
Scala, AWS, Docker, Kubernetes, Postgres, Cassandra, Kafka, Redis, TorchServe, Triton, vLLM, LanceDB, FAISS, Feast, Akka, Erlang, Elixir, Go
Responsibilities
Design and build scalable, high throughput, and low latency distributed systems; Build reusable components for ML applications; Partner with ML engineers to develop scalable solutions; Optimize latency, cost, and efficiency of infrastructure; Mentor engineers on system design and incident management; Define long-term vision and architecture for ML Infrastructure.
Seniority
Staff, hands-on IC with architectural leadership