The Principal Software Architect’s primary role is to own end-to-end integration of our internal compiler into a unified toolchain with runtime, IDE, debugger, profiler, and deployment pipeline. This role requires a strong practical proficiency in ML, particularly in embedded AI, as well as integrating and productizing complex toolchains. The Principal Software Architect will work hand-in-hand with the CTO and silicon team to expose hardware capabilities via software abstractions.
Responsibilities:
- Own end-to-end integration of our internal compiler into a unified toolchain with runtime, IDE, debugger, profiler, and deployment pipeline.
- Define clean APIs, build systems (CMake, Ninja), and packaging (SDKs, Docker, Debian) for internal and external developers.
- Lead development and Integrate LLM-driven features: model-aware code completion, hardware mapping suggestions, auto-optimization hints, and natural-language debugging.
- Design and deliver a unified profiling suite (host + target) capturing: End-to-end latency (software to RTOS to NPU); Power draw (per-core, memory, interconnect).
- Target-Side Bootloader & RTOS Integration.
- Integrate with open-source RTOS for concurrent multi-model support and real-time scheduling on the NPU SoC.
- Collaborate with the CTO and silicon team to expose hardware capabilities via software abstractions.
- Developing and maintaining efficient code in Python, C, and C++ for real-time systems.
Requirements:
- BS/MS Degree in Computer Engineer, Computer Science, Electrical Engineering, or a related field with 7+ years of experience; or a MS Degree with 3+ years of experience integrating and productizing complex toolchains (compilers, IDEs, debuggers, profilers).
- Proven experience with open-source integration and upstream contribution workflows.
- Technical expertise in RTOS & Embedded: Zephyr/FreeRTOS, device trees, linker scripts, bare-metal bring-up.
- Strong background in machine learning and embedded AI applications.
- Expert in C/C++ and Python
- Compiler Integration: LLVM/MLIR tooling, plugin architecture, pass management.
- Experience with ML frameworks such as TensorFlow, Keras, and PyTorch.
- Understanding of computer architecture principles.
Preferred Experience:
- Upstream contributions to VS Code, LLVM, Zephyr, OpenOCD, or other large opensource projects.
- Experience with LLM integration in IDEs (Copilot, CodeLlama, custom fine-tuned models).
- Secure boot and firmware update systems in production devices.
- Strong Background in robotics and embedded system.
Relocation/Immigration Requirement:
- Prefer candidates that reside in the Southern California Area.
- Will provide relocation assistance to the right candidate (that resides in the United States).
- Will transfer H1-B Visa to candidates (that resides in the United States).
- All candidates MUST reside in the United States.
Salary Range:
- $180K – $220K
- Startup Equity (Stock Options)
#machinelearning #ML #artificialintelligence #AI #semiconductor #LLM #RTOS #systemonachip #softwareengineer #embeddedengineer #C++ #python #TensorFlow #PyTorch #toolchain #compilers