Staff Machine Learning Engineer, Taxonomy

Patreon•San Francisco, CA

13d•Hybrid

About The Position

As we scale the platform, understanding what our creators are making and what fans are consuming becomes increasingly important. We’re looking for a Staff Machine Learning Engineer to develop the content and creator classification systems that power discovery, recommendations, and platform insights. This role is based in San Francisco or in New York and open to those who are able to be in-office 2 days per week on a hybrid work model. You'll join the Relevance team, whose mission is to use data to uncover key insights that drive Patreon's product strategy while instilling a culture of curiosity, scientific rigor, and data fluency across the organization. As the first dedicated Taxonomy MLE, you'll sit within the Relevance team — responsible for powering discovery, feed relevance, and creator-fan matching. You'll collaborate closely with the team on shared infrastructure, code reviews, and roadmap alignment, while partnering with Product, GTM, Trust & Safety, and other MLEs to ensure your classification systems serve the full breadth of Patreon's needs.

Requirements

8+ years of experience in ML engineering or applied ML roles
You have expertise in natural language processing, topic modeling, and clustering techniques
You have experience working in an end-to-end machine learning team environment: analyzing data, building and iterating on machine learning models, writing production-level code and shipping to production, monitoring performance, and A/B testing
You have experience working with unstructured content (e.g. audio, video, text, images) and understand how to extract meaning from complex media
You write clean and robust code in Python and have fluency in common ML/NLP libraries
You have experience with distributed systems, production pipelines, and model deployment frameworks
You collaborate effectively across engineering, data science, and product teams
You have solid communication skills and write clear documentation
Bachelor's or Master's degree in Computer Science, Machine Learning, Statistics, or a related field

Responsibilities

Build and deploy machine learning pipelines that generate taxonomies of creators, content, and risk profiles across the platform. These systems enable everything from improved recommendations to content quality signals and search relevance.
Conduct exploratory data analyses and proof-of-concept machine learning models to understand opportunities and potential project impact.
Collaborate with cross-functional partners, such as product, engineering, design, legal, and trust and safety to design effective machine learning solutions.
Analyze and prepare training data, including using crowdsourcing data labeling techniques.
Train and iterate on machine learning models using novel techniques.
Deploy machine learning models to production and write backend code when necessary to properly deploy the model.
Debug models when observability shows performance gaps, and iterate on models.
Translate data into actionable insights and communicate your technical work to cross-functional partners, executive leadership, and the rest of the company.
Be a cultural and technical leader on the Relevance team.