Skip to main content

About the role

Overview: In this role you will define and optimize hardware-software architectures for data processing workloads across NVIDIA’s ADI platforms. You’ll work with end users, partners, and internal teams to align roadmaps with customer needs and achieve high performance at scale. You will drive full-stack performance improvements—from kernels to system IO and data movement—while shaping future hardware features. This is a highly collaborative, impact-driven position at the intersection of data platforms and accelerator technology. Compensation / Benefits equity benefits
Responsibilities: Co-design future architectures for data processing platforms focusing on performance, efficiency, and cost Engage with end users, open-source communities, ISVs, storage partners, and CSPs to inform roadmaps and reference architectures Drive end-to-end performance optimization from CUDA kernels to system-level IO and data movement Collaborate with CPU, GPU, and platform architects to influence hardware features via workload analysis Develop constraint-based frameworks and optimization solvers to navigate trade-offs across metrics Create benchmarking frameworks to measure performance sensitivity and guide co-optimization Analyze production workloads to identify compute motifs, IO patterns, and optimization opportunities across the stack
Key requirements: MS or PhD in Computer Science, Computer Engineering, Electrical Engineering, or related field (or equivalent experience) 8+ years in distributed data platforms, databases, systems engineering, performance architecture, accelerated computing, or HW/SW co-design Deep knowledge in data processing systems, accelerated computing, high-performance IO, CPU/GPU architecture, or large-scale performance analysis Experience evaluating system-level trade-offs across compute, IO provisioning, memory, network topology, and storage across diverse workloads Ability to translate complex system analyses into actionable guidance for silicon architects, software engineers, and leadership Experience working across matrixed organizations to drive alignment and deliver results Hands-on experience with GPU-accelerated data processing (preferred) strong collaboration across cross-functional teams excellent communication and ability to present complex analyses to executives problem-solving mindset with a focus on actionable outcomes CUDA and CUDA kernels cuDF, RAPIDS, cuVS vector databases or structured data engines

Matching similar jobs

JOB OVERVIEW

Experience level

Lead

Location

Brooklyn, NY

Occupation

Computer Systems Engineers/Architects

Industry

Computer Systems Design Services

Posted

today

Tired of running searches?

Rank the roles you'd take once, and matches like these arrive on their own.

CREATE PROFILE (opens in a new tab)