Lead ML Inference & Distributed Systems Engineer

Aimlroles; San Francisco (CA); Remote; USD 227,000 - 325,000; Full time

Benefits offered by this job

Annual bonus

Long-term incentive plan

Medical/Dental/Vision insurance

401(k) plan

Paid time off

Job summary

Tubi is seeking a Staff Software Engineer for the ML Infrastructure team to build world-class ML inference platforms powering recommendations, search, and content understanding. You will advance low-latency model serving, feature/vector stores, and experimentation engines across the ML stack.

You will collaborate with ML, Product, and cross-functional teams to define the long-term architecture, deploy scalable services, and contribute to open-source efforts, with opportunities to influence

Qualifications

• Experience designing and building scalable, distributed systems.
• Proficiency with AWS and distributed systems.
• Experience with SQL and NoSQL databases, and message brokers.

Responsibilities

• Design and build scalable, high throughput, and low latency distributed systems using Scala.
• Build reusable components and services for ML applications like Personalization, Search, Ads and Exploration.
• Partner with ML engineers to address challenges and scale the stack; suggest improvements.
• Lead large-scale cross-functional refactorings to improve latency and cost efficiency.
• Mentor engineers on system design, incident management, and leveraging LLMs.
• Define long-term vision and architecture for ML Infrastructure at Tubi.

Skills

Distributed systems

Scala/JVM

AWS

Microservices

Databases (SQL/NoSQL)

Containers (Docker/Kubernetes)

Incident response

Tools

Kafka

Redis

Postgres

Cassandra

Docker

Kubernetes

Job description

Tubi is seeking a Staff Software Engineer for the ML Infrastructure team to build world-class ML inference platforms powering recommendations, search, and content understanding. You will advance low-latency model serving, feature/vector stores, and experimentation engines across the ML stack.

You will collaborate with ML, Product, and cross-functional teams to define the long-term architecture, deploy scalable services, and contribute to open-source efforts, with opportunities to influence