Member of Technical Staff, System Software (Runtime & Firmware)

Unconventional, Inc.•Mountain View, CA

8d•Onsite

About The Position

Since 2022, AI has entered the mainstream, reshaping entire industries from education and software development to fundamental consumer behaviors. This revolution has created an unprecedented demand for computation - a demand that is now fundamentally limited by energy, not just in the datacenter, but at a global scale. At Unconventional, our mission is to solve this. We are rethinking computing from the ground up to build a new foundation for AI that is 1000x more efficient. We're doing this by exploiting the rich physics of semiconductors, mapping neural networks directly to the device physics rather than relying on layers of inefficient abstraction. As a Member of Technical Staff, System Software (Runtime & Firmware), you will be a foundational member of our small, multi-disciplinary R&D team and have the opportunity to shape and build the software stack for an entirely new type of computer. System Software is the integrator: we compose our novel compute fabrics and our silicon into a working system, and we build the software stack that drives it. “Extreme co-design” is our guiding principle: the stack, the architecture, and the silicon move together, and your work shapes all three from first principles. This role spans runtime software on Linux hosts and embedded firmware on SOCs. You don't need to be an expert in both, but you have to be very strong in one, and solid in the other.

Requirements

B.S. or M.S. in Electrical Engineering, Computer Engineering, Computer Science, or a related field.
7+ years of industry experience in embedded firmware, driver development, or hardware-adjacent systems software, including at least one bring-up of new or prototype silicon and hardware that you took from power-on to running real workloads.
Expertise in C/C++ on embedded processors, including interrupts, DMA, memory-mapped register access, and boot and flash paths.
Experience developing Linux drivers in kernel or user space, with demonstrated depth in at least one of PCIe, USB, UART, or SPI, and in designing robust protocols over an imperfect physical link.
Strong Python engineering alongside your C/C++, and the versioning discipline required when firmware, drivers, and host software each ship independently.
Ability to identify, triage, and solve anomalies across silicon, board, firmware, and software, and to correlate measured behavior against simulation models.
Excellent ability to communicate complex technical concepts to diverse teams across the full stack from algorithms to circuits.

Nice To Haves

Experience building the runtime or driver layer for an AI accelerator, NPU, or GPU, including kernel dispatch, queueing, and memory management.
Experience designing instruction encodings, microcode, or control-flow sequencing for a non-CPU compute engine.
Hands-on experience developing, integrating, and debugging RTL on FPGA platforms, including timing closure and bring-up of prototype boards, plus familiarity with embedded microcontroller IP, PCIe, and the host driver stacks that target such platforms.
Familiarity with cloud infrastructure and deployment, including virtualization, containerization, and running hardware-attached services.
Any exposure to analog, mixed-signal, and/or other unconventional physics-based computing paradigms.

Responsibilities

Build the runtime that executes compiled models on the machine, covering dispatch, data movement, and result readback. One runtime targets both our simulated system model and real silicon, so a program runs on either unchanged.
Design and implement bare-metal firmware on the on-device embedded processor, covering model execution and scheduling, device sequencing, and calibration.
Build and maintain the drivers on both sides of the host/device boundary, along with the protocol between them, including the host-side hardware abstraction layer and the compatibility discipline required when firmware and host software ship independently.
Lead post-silicon software bring-up alongside the Hardware team, own the software that drives our test chips, and close the loop between measured hardware behavior and our simulation models.
Collaborate with the AI, System Modeling, and Hardware teams, our first customers, to get prototype hardware into their hands and keep it running as the platform scales.