ML Engineer L4, Consumer Inference

Netflix is seeking a Machine Learning Engineer to join their Machine Learning Platform (MLP) team. This role will focus on bridging the gap between ML research and productization. Key responsibilities include:

• Developing customer-facing libraries and services for efficient and scalable ML model inference
• Building and maintaining online inference services for real-time predictions
• Optimizing and deploying large language models (LLMs) for production environments
• Maintaining and improving a model registry for ML model governance
• Participating in ML Platform incident management and support

The ideal candidate will have:

• Strong programming skills in Python and Java
• Experience with ML libraries like TensorFlow and PyTorch
• Familiarity with GPU inference optimization tools (e.g., Triton Inference Server, TensorRT)
• Knowledge of containerization (Docker) and orchestration (Kubernetes)
• Experience in large-scale build, release, CI/CD, and observability techniques
• Strong customer focus and excellent communication skills

Netflix offers a unique culture with true transparency and autonomy. The role provides opportunities for impact, responsibility, and continuous learning in a collaborative environment. The company provides comprehensive benefits, including health plans, mental health support, 401(k) with employer match, stock options, and paid time off.

Netflix is committed to diversity and inclusion, providing equal opportunities to all candidates regardless of background.