Senior ML Infra Engineer - Low-Latency Scale

Patreon; New York, San Francisco (NY, CA); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Healthcare

401k with matching

Paid time off

Job summary

Patreon seeks a Senior Machine Learning Engineer, Infrastructure, to design and scale high-throughput ML infrastructure with low-latency live inference capabilities. The role is hybrid, with in-office presence in San Francisco or New York three days a week.

You will own the feature store lifecycle from ingestion to production serving, ensuring data consistency between online and offline features, and will work with product, data engineering, and trust & safety to deliver robust infrastructure.

Qualifications

• Deep experience building, deploying, and maintaining production-grade ML infrastructure at scale, with low-latency live inference pipelines and feature store architectures.
• Strong background in distributed systems and backend engineering, writing robust, maintainable Python code.
• Systematic debugging of high-throughput systems and performance bottlenecks.
• Experience building '0 to 1' infrastructure foundations that stand the test of time.
• Clear documentation for system architectures and infrastructure strategies.
• Growth mindset and improving developer velocity through code reviews.

Responsibilities

• Architect, scale, and maintain high-throughput, low-latency live inference infrastructure to support relevance systems.
• Own the end-to-end feature store lifecycle—from ingestion and transformation to production serving, ensuring high availability and consistency between online and offline features.
• Design and implement observability, monitoring, and validation frameworks to detect performance gaps, latency spikes, and production drift.
• Collaborate with product, data engineering, and trust and safety to translate product requirements into robust, scalable infrastructure solutions.
• Automate model deployment and reliability testing to improve developer velocity and ensure system stability.
• Debug complex relevance systems when monitoring identifies performance bottlenecks or reliability issues.

Skills

ML infra

Low-latency

Python

Distributed systems

Back-end engineering

Documentation

Collaboration

Tools

Kubernetes

Terraform

Airflow

Job description

Patreon seeks a Senior Machine Learning Engineer, Infrastructure, to design and scale high-throughput ML infrastructure with low-latency live inference capabilities. The role is hybrid, with in-office presence in San Francisco or New York three days a week.

You will own the feature store lifecycle from ingestion to production serving, ensuring data consistency between online and offline features, and will work with product, data engineering, and trust & safety to deliver robust infrastructure.