Staff ML Infra Engineer: Low-Latency Distributed Systems

Tubitv; San Francisco (CA); Hybrid; USD 227,000 - 325,000; Full time

Benefits offered by this job

Medical/dental/vision

401(k) plan

Paid time off

Wellness reimbursement

Job summary

Tubi is seeking a Staff Software Engineer for the ML Infrastructure team in San Francisco. You will help design and scale ML inference platforms powering personalization, search, and content understanding across the service.

You’ll own low-latency, distributed backend systems and collaborate with ML engineers to deliver state-of-the-art infrastructure. Hybrid work and strong compensation reflect the strategic impact of this role.

Qualifications

• Experience designing scalable, distributed systems in modern backend languages (Scala/Java/Python/Go/C++).
• Strong experience with cloud platforms like AWS.
• Experience building low-latency online microservices at scale.
• Familiarity with SQL and NoSQL databases, message brokers, and caches.
• Experience with containerization (Docker/Kubernetes).
• Led major incident response and resolution efforts.

Responsibilities

• Design and build scalable, high throughput, low latency distributed systems using Scala.
• Build reusable components and services for ML applications like Personalization, Search, Ads.
• Collaborate with ML engineers to address challenges and keep the Inference stack state of the art.
• Lead large-scale cross-functional refactors focusing on latency, cost, and efficiency.
• Mentor engineers on system design, incident management, and ML utilization in work.
• Define long-term vision and architecture for ML Infrastructure at Tubi.

Skills

Scala

Java

Python

Go

C++

AWS

Distributed systems

Low latency

Postgres

Cassandra

Kafka

Redis

Docker

Kubernetes

Tools

Scala/JVM language

Docker

Kubernetes

Kafka

Postgres

Cassandra

Redis

Job description

Tubi is seeking a Staff Software Engineer for the ML Infrastructure team in San Francisco. You will help design and scale ML inference platforms powering personalization, search, and content understanding across the service.

You’ll own low-latency, distributed backend systems and collaborate with ML engineers to deliver state-of-the-art infrastructure. Hybrid work and strong compensation reflect the strategic impact of this role.