This is a fully remote position, open to applicants in California.

📋 Description

• Create top-tier GPU-accelerated software for AI inference serving.

• Engage in feature development and promote widespread customer adoption.

• Lead the integration of the Triton Inference Server with NVIDIA Dynamo stacks to create a cohesive, high-performance inference platform.

• Actively participate in the open-source deep learning software engineering community.

• Manage a range of objectives including developing robust software for deployment in production server or cloud settings, optimizing and balancing prediction throughput and latency, and innovating the next generation of inference technologies.

⛳️ Requirements

• Currently pursuing or have recently completed a Master's or PhD in Computer Science or a related discipline (or possess equivalent experience).

• Proficient in Rust or C++, with familiarity in Python, and possess strong programming and software design capabilities, including debugging, performance analysis, and test design.

• Experience with large-scale distributed systems and machine learning systems.

• Excellent communication skills and the ability to thrive in a dynamic, agile team environment.