NVIDIA
Senior Software Engineer, C++ and CUDA - Analytics and Data Intelligence
$184K–$356K
US, CA, Santa Clara +5 · Senior · Full-time · Posted Aug 14, 2026
- Location
- US, CA, Santa Clara
US, TX, Remote
US, NY, Remote
US, WA, Remote
US, CA, Remote
US, MA, Remote - Experience
- 8+ years of experience in Computer Science or Software Engineering.
- Education
- MS degree or PhD in computer science, engineering, or a related field, or equivalent experience.
About the job
Develop and optimize open-source GPU data-processing libraries and distributed query-engine features, including GPU-to-GPU communication and analytical workloads.
What you'll do
- Own development of UcxExchange in Velox, including its feature roadmap, performance, and correctness.
- Optimize multi-node performance for analytical queries with Presto GPU across on-premises clusters and public cloud servers.
- Lead projects in Presto, Velox, and cuDF, such as operator completeness, GPU memory oversubscription, and efficient CPU fallback.
What they ask for
- Strong Modern C++ programming skills.
- Care deeply about robust, readable, high-performance code.
Nice to have
- Expertise in high-performance communication protocols (e.g., UCX, NCCL) and distributed algorithms for query engines; familiarity with RAPIDS cuDF.
- Experience in distributed workflow development and debugging; passion for open-source development and publishing technical work.
Pay
184,000 USD - 287,500 USD base salary (Level 4); 224,000 USD - 356,500 USD base salary (Level 5)
Tools
Modern C++, CUDA, UCX, NCCL, RAPIDS, cuDF, Presto, Velox
AI focus
The role develops GPU-accelerated data-processing software relevant to LLM training. NVIDIA also states that it uses AI tools in its recruiting processes.
Model-written summary · the original posting is authoritative