Machine Learning Engineer, Fast Optimized Inference - US Remote

View full description

Requirements:

• Proficient with Python, Rust and specialized Cuda kernels.
• Experience with transformers frameworks such as Keras or PyTorch.

Responsibilities:

• Develop specialized software for specific machine learning (ML) use cases that have broad applications, similar to text-generation-inference.
• Utilize existing library frameworks to create scalable software solutions for industrial purposes.
• Enhance the reliability, quality, and time-to-market of our software suite.
• Measure and optimize system performance to stay ahead of customer needs and drive innovation.
• Manage the production environment by monitoring availability and ensuring overall system health.