Senior Software Engineer, C++, CUDA – Analytics, Data Intelligence

This is a fully remote position, open to applicants in California, +3 more states.

📋 Description

• Take charge of the development of “UcxExchange” within Velox, focusing on GPU-to-GPU communication in Presto.

• Lead the feature roadmap, enhance performance, and ensure accuracy.

• Optimize multi-node performance for analytical queries utilizing Presto GPU.

• Aim at both on-premises clusters and public cloud servers.

• Spearhead projects in Presto, Velox, and cuDF, addressing operator completeness, GPU memory oversubscription, and efficient CPU fallback.

• Provide innovative contributions to NVIDIA’s open-source software collection.

• Expedite database and DataFrame operations across various hardware, from single workstations to multi-node GPU supercomputers.

⛳️ Requirements

• Over 8 years of experience in Computer Science or Software Engineering.

• MS degree or PhD in computer science, engineering, or a related discipline, or equivalent professional experience.

• Proficient in Modern C++ programming.

• Dedication to producing robust, clear, and high-performance code.

• Knowledgeable in high-performance communication protocols like UCX and NCCL.

• Understanding of distributed algorithms applicable to query engines.

• Familiar with RAPIDS cuDF.

• Experienced in developing and debugging distributed workflows.

• Enthusiastic about open-source software development.

• History of publishing work in technical blogs and presenting at conferences.

🏝️ Benefits

• Competitive salaries.

• Comprehensive benefits package.

• Equity options.

• Equal opportunity employer.

• Supportive and inclusive work environment.