Senior System Software Engineer – SDK and Algorithms

Overview

• As the top tier artificial intelligence computing company, we are paving the way with innovations in self-driving cars, machine learning, super-computing, gaming, and visualization.
• We are building a team that will truly change the world and would love for you to join us.
• We are seeking a senior system software engineer to design and code computer vision software and help create the SDK for our Programmable Vision Accelerator (PVA) engine in the Tegra SoC platform.
• You will join a team of skilled software developers in crafting highly optimized computer vision, signal processing and machine learning algorithms for specialized DSP hardware.
• You will also help other internal and external customers to efficiently develop or map and optimize complex algorithms on the PVA’s VLIW/SIMD hardware.
• And you will also enhance the PVA SDK which enables others to develop for the PVA.
• We seek engineers with excellent leadership, communication, interpersonal, and analytical skills as well as a real passion for computer vision.
• What you will be doing: Develop and improve the SDK for internal and external customers who are developing on the PVA.
• Develop and Optimize Algorithms to efficiently run on PVA.
• Work with internal and external customers to help them develop and optimize algorithms on the PVA.
• Provide technical leadership through your software development experience.
• Help set technical direction and feature set for the PVA SDK.
• Write effective, maintainable, and well-tested code.
• Enable automated testing.
• Collaborate, learn, and grow skills with NVidians.
• What we need to see: Bachelor's or MS in Electrical Engineering, Computer Engineering, Computer Science or related field (or equivalent experience).
• 8+ years of work experience writing high-performance software.
• Consistent record of developing high-performance computer vision, image processing, radar or lidar signal processing software on DSPs, GPUs and/or CPUs.
• Deep familiarity with SDKs for heterogeneous accelerators and understanding of the necessary components including compilers, debuggers, profilers, runtime APIs, documentation.
• Strong software development skills in C++, including low-level debugging and performance profiling.
• Experience with Linux-based or QNX development environments.
• Ability to write clear technical documentation.
• Strong communication and interpersonal skills.
• Ways to stand out from the crowd: Direct experience designing and shipping a programming model for a programmable hardware accelerator and programming in SIMD/VLIW processors.
• Experience with compiler, debugger, linker or toolchain development, particularly using LLVM.
• Background with ISO 26262 and IEC 61508 or equivalent quality/safety processes.
• Demonstrated ability to use agentic AI tools effectively as a force multiplier in day-to-day engineering, including prompt design, agent orchestration, and validating AI-generated code in performance-critical or safety-critical contexts.
• Curiosity about applying LLMs and agentic workflows to DSP and accelerator SDK problems, such as auto-generating kernels, optimizing schedules, synthesizing test vectors, or building AI-assisted developer experiences for PVA users.
• NVIDIA is widely considered to be one of the technology world’s most desirable employers.
• We have some of the most forward-thinking and hardworking people in the world working for us.
• If you're creative and autonomous, we want to hear from you.
• NVIDIA is leading the way in groundbreaking developments in Artificial Intelligence, High-Performance Computing and Visualization.
• The GPU, our invention, serves as the visual cortex of modern computers and is at the heart of our products and services.
• Our work opens new universes to explore, enables amazing creativity and discovery, and powers what were once science fiction inventions from artificial intelligence to autonomous cars.
• NVIDIA is looking for phenomenal people like you to help us accelerate the next wave of artificial intelligence.