Software Engineer L5, LLM Compute & Serving Systems

Netflix is seeking a strong senior engineer to own and develop the long-term vision for their Consumer ML Serving team. This team provides the computational platform for building nearly all consumer-facing ML/AI applications, including real-time model serving, event-driven model and feature compute, and distributed compute orchestration. The role involves expanding LLM innovation in personalization areas and building model serving infrastructure for LLMs and other large foundation models.

Key responsibilities include:

• Developing scalable, robust systems for ML/AI initiatives
• Partnering cross-functionally with engineers, product managers, ML engineers, and data scientists
• Delivering high-quality, well-tested code in ambiguous environments
• Executing 0-to-1 projects
• Supporting large-scale ML models with direct customer impact
• Leading projects with 3-4 other engineers

Ideal candidates should have:

• Experience with high-traffic, real-time distributed systems and ML serving infrastructure for LLMs
• Proficiency in object-oriented programming (primarily Java)
• DevOps experience for large applications
• Familiarity with public cloud platforms (AWS, Azure, or GCP)
• Strong communication skills and bias towards action
• BS/MS in Computer Science, Applied Math, Engineering, or related field

Netflix offers a unique culture and environment, emphasizing diversity and inclusion. The compensation structure includes an annual salary range of $100,000 - $720,000, with the option to choose between salary and stock options. Comprehensive benefits include health plans, mental health support, 401(k) with employer match, stock options, and various leave programs.

Join Netflix to push the boundaries of ML/AI technology and directly impact the streaming experience for millions of users worldwide.