Senior AI Software Architect - Runtime

About the role

Join the team building Intel's product-grade neuromorphic AI execution stack targeting edge and robotic systems. In this role, you will architect and lead the development of the firmware, runtime, and performance infrastructure, working closely with hardware, compiler, systems, and application teams to deliver a robust, observable, and high-performance software stack. You will set technical direction for a critical part of the platform while remaining hands-on in architecture and implementation.

Responsibilities

• Define and drive the technical vision, architecture, and roadmap for Intel's neuromorphic runtime software stack, while contributing hands-on to critical design and implementation.
• Architect, develop, and optimize firmware and runtime components, including execution control, scheduling, data movement, memory management, and device interfaces.
• Architect and deliver performance infrastructure, including profiling, tracing, debugging, benchmarking, and regression frameworks needed for optimization and product release.
• Integrate the runtime stack into existing robotics and edge software ecosystems, to enable efficient deployment and developer adoption.
• Collaborate with hardware, compiler, systems, application, and solution teams, as well as customers and external partners, to translate platform and workload requirements into robust software capabilities.
• Provide technical leadership across the runtime area by establishing engineering practices, driving software quality and release discipline, mentoring engineers, and helping scale the team over time.

Qualifications

• BSc, MSc, or PhD in Computer Science, Electrical/Computer Engineering, Physics, Mathematics, or a related technical field.
• 5+ years of experience developing firmware, runtime, performance, or other low-level systems software for AI or accelerators, including execution environments, profiling, debugging, and related infrastructure, with experience in technologies such as CUDA, LLVM, oneAPI, SYCL, ONNX, IREE, OpenVINO, TVM.
• 5+ years of experience leading software architecture for complex AI, runtime, or accelerator software systems, including defining technical direction and guiding implementation.
• 8+ years of experience developing maintainable, production-grade software in C/C++ and Python, including systems-level and performance-critical code, using disciplined engineering practices such as benchmarking, correctness and performance regression testing, build/toolchain management, and CI/CD.
• 5+ years of experience with AI, deep learning, or optimization workloads using frameworks such as PyTorch, JAX, or TensorFlow.

Preferred Qualifications

• Experience managing and mentoring engineers, and leading delivery across cross-functional teams spanning hardware, systems software, compiler, and applications.
• Experience with robotics, edge, or real-time systems, including software ecosystems such as ROS2.
• Experience in HW/SW co-design, hardware simulator development, or software bring-up for emerging accelerator architectures.
• Experience with parallel computing paradigms or spatial / unconventional AI hardware accelerators.
• Experience with embedded or real-time Linux, device-driver / platform bring-up, or other low-level deployment software for edge systems.
• Prior contributions to open-source software projects.