Systems Software Engineer

Job Title

Systems Software Engineer

Role Summary

Join the Systems Team to build and maintain the low-level software stack for a General-Purpose Neural Processing Unit (GPNPU). You will implement and own components such as the instruction-set simulator, loader/assembler, debugger backends, and C++ host/device APIs that connect SDKs to custom hardware.

Experience Level

Mid-level (5+ years of relevant systems software experience).

Responsibilities

Primary responsibilities focus on developing and maintaining foundational toolchain, simulator, debugger, and host API components that enable software and hardware co-design.

• Maintain and optimize the instruction-set simulator used for architecture validation and software development.
• Design and implement loader and assembler functionality, including binary formats (e.g., ELF) and efficient code loading.
• Develop and extend remote debugger backends, breakpoints, and memory inspection facilities.
• Design, implement, and document clean C++ host and core device APIs for SDK and customer use.
• Collaborate with hardware and SDK teams to identify execution trade-offs and influence hardware and software specifications.
• Deliver production-ready, low-latency abstractions and debugging utilities used by internal and external developers.

Requirements

Must-have technical skills and domain experience; preferred items listed separately.

• Minimum 5 years building systems software such as simulators, toolchains, debuggers, drivers, or performance-critical C++ libraries.
• Strong modern C++ (C++17/20) skills and systems-level programming practices.
• Deep understanding of RAII, manual memory management, object lifetimes, ownership models, and memory access optimization.
• Experience designing and maintaining clean abstraction layers and public APIs.
• Proven ability to work at the hardware/software boundary (e.g., architectural simulation, debugger internals, low-level toolchains, or bare-metal performance code).
• Experience with ELF/binary formats, loaders, assemblers, or linkers where applicable.

Preferred:

• Familiarity with CPU/NPU pipelines, registers, caches, and silicon constraints.
• Experience with GPU/acceleration programming (CUDA, OpenCL, Vulkan) and host-to-device memory transfers.
• Linux driver development and CMake-based build systems.
• Exposure to Rust for systems safety, and experience reasoning about concurrency and synchronization.
• Knowledge of functional programming concepts applied in low-level environments.

Education Requirements

Not specified.

About the Company

Company: Quadric

Headquarters: Burlingame, California, United States

Quadric is building the world’s first supercomputer designed for the real-time needs of edge devices. Founded in 2016, the company empowers developers across industries with innovative general-purpose neural processing unit (GPNPU) architecture for neural network workloads. Co-founded by technologists from MIT and Carnegie Mellon, Quadric aims to enable groundbreaking technology development.