Q

Quadric

GPNPU hardware and software for ML

Systems Software Engineer

Systems Software EngineeringConfirmed live in the last 24 hours
Full-timeBurlingame, CA, USA

About the Job

Requirements

  • At least 5 years of experience building systems software, including simulators, toolchains, debuggers, drivers, or performance-critical C++ libraries.
  • Deep comfort with modern C++ (C++17/20) and systems-level programming paradigms.
  • Advanced understanding of RAII, manual memory management, object lifetimes, ownership models, and memory access optimization.
  • Ability to identify, design, and maintain clean abstraction layers that result in readable, maintainable, and scalable code.
  • Demonstrated experience tackling complexity at the hardware/software boundary in at least one of these areas: architectural simulation using cycle-accurate or functional simulators; debugger backends involving breakpoints, memory inspection, GDB stubs, or remote protocols; shipping C++ SDKs or libraries balancing zero-cost abstractions with intuitive user interfaces; low-level toolchains including assemblers, linkers, or loaders, with knowledge of binary formats such as ELF and memory layouts; or performance-critical bare-metal code such as drivers or embedded firmware.

Responsibilities

  • Maintain and optimize the instruction set simulator used for architecture validation and software development, influencing hardware and software co-design decisions.
  • Drive the design of the low-level toolchain, including efficient translation, binary execution (for example, ELF formats), and code loading.
  • Develop, enhance, and refine remote debugging tools and backends that provide low-level visibility into GPNPU execution.
  • Design, maintain, and document abstraction layers and public C++ APIs that allow users and SDKs to interact with the hardware.
  • Own and expand one or more key systems-stack components, such as the simulator, loader/assembler, debugger, or C++ host APIs.
  • Identify execution trade-offs in the instruction set simulator to influence next-generation GPNPU hardware and software specifications.
  • Deliver production-ready, low-latency API abstractions and debugging utilities for internal SDK developers and external customers.

Desired Qualifications

  • Understanding of CPU/NPU pipelines, registers, caches, and silicon-level constraints.
  • Experience with CUDA, OpenCL, or Vulkan, SIMD/SIMT architectures, and host-to-device memory transfers.
  • Experience with Linux driver development and CMake project configuration best practices.
  • Familiarity with Rust for systems safety and with reasoning about multithreaded logic and complex synchronization issues.
  • Knowledge of integrating functional programming concepts in non-garbage-collected environments.

About the Company

Quadric

GPNPU hardware and software for ML

Quadric.io provides an integrated hardware-software platform for ML on System-on-Chips, centered on its Chimera General-Purpose Neural Processing Unit (GPNPU). Developers write ML code in C, which is compiled by the Chimera LLVM C Compiler, simulated with the Chimera Instruction Set Simulator (ISS), and deployed via a Software Development Kit (SDK) that supports design, profiling, and execution on Chimera. The solution is a single, end-to-end pipeline that eliminates the need to partition code across DSPs/GPUs and CPUs, offering tightly integrated hardware and software tools that can run a wide range of C-based neural-network operations. Quadric.io aims to simplify and accelerate the design of ML-enabled SoCs for semiconductor developers and manufacturers, enabling faster time-to-market and better ML performance through its cohesive hardware-software stack.

Company size
51-200
Company stage
Series C
Total funding
$94.3M
Headquarters
Burlingame, CA
Founded
2017

Recently Posted Jobs

Explore more opportunities at Quadric

See more jobs