Want to know if this job is worth applying to?
San Jose, California, United States
Onsite
About Etched
Etched is building hardware for frontier intelligence. We co-design chips, racks, software, and manufacturing to deliver best-in-class throughput and latency across both prefill and decode workloads. Our first products are heavily focused on inference. Backed by hundreds of millions from top-tier investors and staffed by leading engineers, Etched is redefining the infrastructure layer for the fastest growing industry in history.
Job Summary
This role owns the accelerator software that turns our custom hardware into an inference system. You'll work across the stack from first power-on through inference execution: bringing CPUs and boards to life, moving data between host and device, and translating inference requests into low-level operations that execute directly on the accelerator. The work spans ASIC software, platform firmware, and host-side kernel and drivers. We hire engineers who are deep in one area and curious about the others.
This role spans across three work areas. You would specialize in one and contribute across the others as the team grows:
ASIC Software — Build the software that runs directly on the accelerator. Work includes CPU initialization, RTOS, boot ROMs and bootloaders, MMU and IO drivers, ASIC/FW architecture and co-design, and on-device inference execution. Translate inference software requests into low-level device operations and scheduling decisions at nanosecond-level timescales to minimize overhead for highly interactive MoE and dense models.
Platform Software — Build the microcontroller and FPGA firmware that brings our custom hardware from powered off to operational. Own areas including power sequencing, board bring-up, telemetry, firmware updates, thermal and power management, and fault detection and recovery. Work directly with hardware engineers through schematic design, bring-up, validation, and production.
Host-side Kernel and Drivers — Build the software that connects the accelerator to the host and exposes it to the inference stack. Work includes Linux kernel and device drivers, PCIe and DMA, high-speed peripheral interfaces, memory management, FLR and virtualization/SR-IOV, and high-throughput, low-latency ring-buffer command flows.
You may be a good fit if you have
Bachelor's degree or equivalent practical experience.
Strong C/C++ and software engineering fundamentals.
Experience building and debugging low-level software that interacts directly with hardware.
Depth in one or more of firmware, embedded systems, device runtimes, operating systems, or kernel/driver development.
Experience shipping software on real hardware into production.
Familiarity with technologies such as ARM, PCIe, DMA, HBM, DRAM, Ethernet, UART, RTOS, or FPGA systems.
Strong systems intuition around performance, concurrency, memory, reliability, and fault handling.
Strong candidates may also have experience with (Nice-to-have qualifications)
Hardware bring-up experience on a new chip or board.
Experience with boot ROMs, secure boot, MMUs, RTOS, or CPU initialization.
Experience with PCIe virtualization, FLR, SR-IOV, DMA, ring buffers, or high-speed device communication.
Experience building accelerator runtimes, schedulers, command processors, or other latency-critical execution systems.
Experience using architecture details such as caching, memory hierarchy, or on-chip fabrics to make software decisions at nanosecond-level timescales.
Experience solving ambiguous problems where the hardware and software architecture evolve together.
Strong communication across firmware, hardware, architecture, kernel, and inference teams.
Benefits
Medical, dental, and vision packages with generous premium coverage
$500 per month credit for waiving medical benefits
Housing subsidy of $2,500 per month for those living within walking distance of the office
Relocation support for those moving to San Jose (Santana Row)
Various wellness benefits covering fitness, mental health, and more
Daily lunch + dinner in our office
Unlimited compute budget subject to ROI justification
How we’re different
Etched believes in the Bitter Lesson. We are the first inference-focused frontier AI system. Our addressable market is the entirety of inference, unlike many of our competitors.
We are a fully in-person team in San Jose (Santana Row), and greatly value engineering skills. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both and work across disciplines as needed.