Solutions Architect - High-Performance Databases

Employment Type: Full time

Position Overview

NVIDIA is seeking a Solutions Architect for High-Performance Databases. This role involves researching new algorithms and memory management techniques to accelerate databases on modern computer architectures. You will investigate hardware and system bottlenecks, and optimize the performance of data-intensive applications. This is an opportunity to work at the forefront of technology with significant visibility and impact on NVIDIA's success.

NVIDIA has a history of innovation, from the GPU's impact on PC gaming and graphics to revolutionizing parallel computing and igniting modern AI. We are a "learning machine" that constantly evolves, tackling challenging problems with unique solutions that matter to the world. Join our diverse team and contribute to amplifying human imagination and intelligence.

What You Will Be Doing

• Research and develop techniques to GPU-accelerate high-performance database, ETL, and data analytics applications.
• Collaborate with technical experts from industry and academia to perform in-depth analysis and optimization of complex data-intensive workloads, ensuring optimal performance on current GPU architectures.
• Influence the design of next-generation hardware architectures, software, and programming models in collaboration with NVIDIA's research, hardware, system software, libraries, and tools teams.
• Partner with industry and academic institutions to push the boundaries of data processing using NVIDIA's full product line.

Requirements

• Master's or PhD in Computer Science, Computer Engineering, or a related computationally focused science degree, or equivalent experience.
• 4+ years of experience.
• Programming fluency in C/C++ with a deep understanding of algorithms and software design.
• Hands-on experience with low-level parallel programming, such as CUDA (preferred), OpenACC, OpenMP, MPI, pthreads, TBB, etc.
• In-depth expertise in CPU/GPU architecture fundamentals, particularly memory subsystems.
• Domain expertise in high-performance databases, ETL, data analytics, and/or vector databases.
• Good communication and organization skills, with a logical approach to problem-solving and prioritization.

Ways to Stand Out

• Experience optimizing/implementing database operators or query planners, especially for parallel or distributed frameworks (e.g., production databases or Spark).
• Background in optimizing vector database index build and/or search.
• Experience profiling and optimizing CUDA kernels.
• Background with compression, storage systems, networking, and distributed computer architectures.

About Data Analytics at NVIDIA

Data Analytics is a rapidly growing field in GPU-accelerated computing. Traditionally CPU-bound data preprocessing and data engineering are becoming bottlenecks for Machine Learning (ML) and Deep Learning (DL) applications, as the performance of ML/DL frameworks and libraries has been highly optimized using GPUs. Many modern applications feature complex data analytics pipelines that can benefit from optimizations in memory management, compression, parallel algorithms (like sort, search, join, aggregation, groupby), scaling to multi-GPU systems, and scaling out to many nodes.

Explore some open-source projects contributed by NVIDIA employees: RAPIDS cuDF, NVIDIA nvcomp, NVIDIA Distributed join, NVIDIA cuCollections.

NVIDIA is recognized as one of the most desirable employers in the technology world, with forward-thinking and dedicated individuals. If you are creative and autonomous, we encourage you to apply.