TixelJobs
N
Netflixvia muse

Engineering Manager, Online Serving and Inference, AI Platform

REMOTE$523K - $920K/yrPosted 1w ago
ML EngineerLeadFull-time#remote

About the Role

At Netflix, our mission is to entertain the world. Together, we are writing the next episode \- pushing the boundaries of storytelling, global fandom and making the unimaginable a reality. We are a dream team obsessed with the uncomfortable excitement of discovering what happens when you merge creativity, intuition and cutting\-edge technology. Come be a part of what’s next.





**The Team**
============





Artificial Intelligence (AI) and Machine Learning (ML) power the innovation in all areas of the business, including helping members choose the right title for them through personalization, better understanding our audience and our content slate, creating high\-quality subtitles, dubbings, images, trailers, and other assets, optimize our payment processing, and much more. The Artificial Intelligence (AIP) organization builds highly scalable and differentiated AI/ML infrastructure to maximize the business impact of all AI practitioners at Netflix, which is the key to accelerating this innovation.





**The Opportunity**
===================





The Online Serving and Inference team builds and maintains the infrastructure that enables ML practitioners to run their large\-scale online serving and inference workflows to deploy AI models for Netflix member scale ecosystems. The team is responsible for the common framework to develop and deploy AI/ML models in Netflix infrastructure to power the AI applications and features.





We are looking for an experienced AI/ML infrastructure engineering leader to lead the development of our next\-generation serving and inference platform! You will lead this team to architect, design, develop, test, and launch a brand\-new platform to enable ML practitioners across the content, studio, consumer, ads, and games domains to effortlessly package, deploy, and execute inference workflows for thousands of large\-scale models, including Large Language Models (LLMs), computer vision and foundation models. The models will come from various lifecycle stages, including early research and experimentation, development, productization, and ongoing innovation and optimization of productized models.





We are a highly collaborative team. You will be highly cross\-functional in partnering with other engineering, product management, machine learning, and data teams to take Netflix’s AI initiatives to the next level. To succeed in this role, you will need a strong AI/ ML infrastructure background and a passion for building scalable, robust systems that enable and accelerate our ability to apply large and complex ML models across various domains.





**In this role, you will:**
===========================





* Partner with Applied Research and backend application teams to understand their needs and gather and iterate on the platform's requirements.
* Drive the architecture, design, build vs. buy evaluation, and execution of the online serving and inference platform. Strive for extensibility and ensure the platform can scale to meet the needs of the evolving AI landscape.
* Build a roadmap focused on incremental delivery. Define success metrics, align on migration goals, and drive the platform's adoption.
* Communicate progress to stakeholders, customers, and senior leadership.
* Maintain existing platform offerings, balancing immediate needs in current systems while prioritizing the development of the next\-gen platform.
* Hire and grow diverse, highly talented engineers while maintaining and fostering an inclusive team culture.




**To succeed in this role, you will need:**
===========================================





* 10\+ years of software engineering experience and 3\+ years of management experience.
* Experience leading teams responsible for building high\-traffic distributed systems and ML infrastructure
* Experience with containerization and orchestration technologies to support data preparation, processing, and inference for large\-scale AI/ML mode
Share