Senior Software Engineer - Autonomous Vehicles

Self-driving cars need to detect the road’s course instantly, without relying on prior maps. We build an online mapping system that transforms raw sensor data into an accurate, live 3D model. This model shows lanes, boundaries, crosswalks, intersection structure, and traffic control semantics that the driving stack depends on. This is a software engineering role is central to that system. The algorithms are only as good as the software that runs them, so we need an engineer who obsesses over quality, performance, and architecture, and who can turn algorithmic ideas into safe, fast, maintainable code that runs in production vehicles on NVIDIA DRIVE Orin and Thor. The software you write will meet ASIL-B/D requirements and ship across L2++, L3, and L4 programs. You won’t be developing the algorithms from scratch, but you’ll need a strong grasp of them. You’ll work closely alongside algorithm engineers, and you need to understand what the code is doing to implement, optimize, and test it well.

What you’ll be doing:

• Build and own core online mapping software operating in the car, from architecture through implementation to deployment.
• Write production C++ for real-time embedded systems, with a focus on correctness, determinism, and maintainability.
• Build software architecture and frameworks that promote code reuse, clean interfaces, and long-term maintainability across vehicle programs.
• Improve performance of C++ and CUDA code running on NVIDIA DRIVE Orin and Thor, employing profilers to detect and address bottlenecks and to meet real-time budgets.
• Use GPU parallelism (CUDA) to make compute-heavy mapping components fast and efficient.
• Implement and incorporate algorithmic solutions from the mapping team into the core of NVIDIA’s AV stack, collaborating with algorithm engineers to understand and improve them.
• Develop according to automotive safety standards (ASIL-B/D). Employ thorough static analysis and adhere to coding guidelines committed to safety. Reach 100% line and branch coverage through detailed unit and integration tests.
• Handle real-time system signals from vehicles operating around the world, building software that is robust to varied conditions and failure modes.
• Collaborate with perception, localization, planning, and infrastructure groups to incorporate online mapping into the complete AV stack across L2++, L3, and L4 programs.

What we need to see:

• BS or MS in Computer Science, Electrical Engineering, or a related field, or equivalent experience.
• 5+ years of validated experience building robust, production-quality software.
• 3+ years of professional C++ development experience, including modern C++ and a strong grasp of memory management, concurrency, and performance.
• Experience designing software architecture and APIs for large, long-lived codebases.
• A quality-first mentality: comfortable with static analysis, unit testing, and high-coverage test strategies.
• Solid understanding of algorithms and data structures, and the ability to work with algorithm developers and understand their work.
• Strong communication and analytical skills, and the ability to work optimally across multiple teams.
• Autonomous and responsible, demonstrating outstanding teamwork while enjoying solving hard problems.

Ways to stand out from the crowd:

• Software development on embedded, real-time, or automotive platforms, including experience with real-time operating systems (e.g., QNX, Linux RT).
• Experience with functional safety standards and processes (ISO 26262, ASIL-B/D), MISRA or AUTOSAR C++ coding guidelines, and safety-qualified toolchains.
• Experience achieving high or full structural coverage (line and branch, ideally MC/DC) on production code.
• Experience with GPGPU programming (CUDA) and GPU performance tuning.
• Strong skills in runtime profiling and optimization of CPU and GPU code.

#AutonomousVehicles

You will also be eligible for equity and benefits.

This posting is for an existing vacancy.

NVIDIA uses AI tools in its recruiting processes.