Inworld AI

You will be responsible for optimizing multimodal model inference and managing high-performance serving systems at scale. This involves taking models from research to production, ensuring reliability, and handling thousands of concurrent connections.

You will be responsible for optimizing multimodal model inference and ensuring reliable, high-performance serving at scale. This involves taking models from research to production, containerizing them, and managing distributed systems to handle thousands of concurrent queries.

The role involves tackling unclear problems and making them clear through rigorous research design and execution. Researchers are expected to own the entire research lifecycle, from framing questions and running experiments to writing papers and shipping results.

You will be responsible for researching, building, optimizing, and deploying production ML systems. Your work will focus on solving complex research and engineering problems related to AI-driven software.