Software Engineer 4/5 – Model Serving Systems, AI Platform

Netflix is a global entertainment company using machine learning and artificial intelligence to power personalization, content understanding, and revenue-focused initiatives. The Software Engineer will develop and expand scalable model-serving and compute infrastructure for AI/ML applications, including large language models, while collaborating cross-functionally to advance Netflix’s AI capabilities.

Responsibilities:

• Develop and expand our compute infrastructure to support the growing AI needs, enable the application of ML in new business areas, and drive AI/ML innovation across Netflix
• Partnering with other engineers, product managers, machine learning engineers, and data/research scientists

Requirements:

• • You have experience building high-traffic distributed services and infrastructure for online ML model inference and are familiar with supporting large-scale ML models focusing on high availability and performance
• • You understand scalable model-serving solutions for generative models and LLMs, with skills in reducing latency and costs, and can solve bottlenecks to streamline research-to-production workflows
• • You are proficient in object-oriented programming (preferably Java) and demonstrate engineering excellence in production hosting, including performance tuning, deployment management, and capacity planning
• • You are familiar with deploying ML models using tools like Triton Inference Server, TensorRT, Docker
• • You are experienced working with the public cloud like AWS, Azure, or GCP
• • You are a proactive communicator who promotes best practices in observability and logging
• • You have a BS/MS in Computer Science, Applied Math, Engineering, or a related field
• Java