Senior Software Engineer, Low-Latency Physical AI Sensor Systems

Details

At NVIDIA, we’re redefining how machines perceive and interact with the world. The Holoscan Sensor Bridge (HSB) streams massive volumes of sensor data—including cameras, radar, RF, and medical devices—directly into GPU memory with low latency to enable real-time AI. It enables real-time signal processing with microsecond-level latency, direct streaming of sensor data into GPU memory, and scalable, software-defined sensor integration across industries. The work supports surgical robotics, autonomous systems, industrial automation, and next-generation scientific instrumentation.

This role focuses on architecting and scaling the software backbone that connects the physical world to accelerated computing, bringing together hardware, networking, and GPU computing for robotics, healthcare devices, and industrial AI systems.

Responsibilities

• Design and build high-performance, low-latency data pipelines from sensors to GPU memory using RDMA, Ethernet, and GPUDirect.
• Develop and optimize system software, drivers, and APIs for sensor integration and streaming.
• Work across the stack, from FPGA interfaces and networking protocols to CUDA and application frameworks.
• Enable seamless integration of diverse sensors into the Holoscan ecosystem.
• Debug and optimize real-time distributed systems under strict latency and throughput constraints.
• Collaborate with hardware, firmware, and AI teams to deliver end-to-end solutions.
• Contribute to a platform that reduces sensor integration complexity by orders of magnitude.

Requirements

• Bachelor’s or master’s degree in Computer Science, Computer Engineering, or a related field, or equivalent experience.
• 8+ years of experience in systems programming with C, C++, or Python and Linux internals.
• Deep understanding of networking, including TCP/UDP, RDMA, kernel bypass, and high-throughput systems.
• Experience with real-time operating systems or low-latency systems.
• Familiarity with hardware/software interfaces such as PCIe, DMA, FPGA, SPI, I2C, and I2S.
• Solid debugging skills across complex, multi-component systems.
• Experience working close to hardware and performance bottlenecks.
• Solid understanding and hands-on experience with AI coding tools such as Claude, Codex, and Cursor, including automating software development lifecycle activities.

Preferred Qualifications

• Experience with CUDA or GPU programming.
• Knowledge of sensor pipelines, including camera, radar, RF, medical imaging, and IMU sensors.
• Exposure to distributed systems or edge computing platforms.
• Background in robotics, healthcare devices, or high-speed data acquisition.
• Familiarity with agentic AI tooling and experience applying multi-agent systems to engineering workflows.

Benefits

• Competitive salary.
• Equity and benefits.
• NVIDIA is committed to fostering an inclusive work environment and is an equal opportunity employer.

Applications will be accepted at least until July 6, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes.