ASIC Firmware Engineer, Modeling

San Francisco. Posted 9 months ago

The role

This role involves building firmware and associated modeling software for an in-house AI accelerator. The engineer will design drivers and functional models, write high throughput and low latency firmware code, and investigate bring-up and production issues.

What you will do

Design and implement drivers for hardware peripherals, including those related to AI chips.
Design and implement functional software models to simulate SoC uncore logic and enable FW testing against the model.
Design and implement low-latency and high throughput embedded SW to manage HW resources.
Work with adjacent software and hardware teams to implement requirements, debug issues and shape future generations of the hardware.
Collaborate with vendors to integrate their technologies within our systems.
Bring up and debug firmware/driver on new platforms.
Come up with processes and debug issues raised in the field.
Set up monitoring, integration testing and diagnostics tools.

Required qualifications

5+ years of experience working in embedded SW space.
Ability to thrive in ambiguity and learn new technologies.
Strong programming skills in C/C++ and/or Rust.
Experience developing high throughput, low latency and multi-threaded code.
Experience working with real time operating systems (RTOS).
Experience developing hardware drivers and working with hardware.
Experience with HW/SW co-design.
Knowledge of common embedded protocols, e.g. UART, I2C, SPI, etc.

Nice to have

Knowledge of microprocessor and common ARM architectures (e.g. AMBA)
Knowledge of PCIe, ethernet and other high BW communication protocols
Experience with GPUs or other compute hardware
Experience deploying large compute clusters

Before you apply

Candidates for this role may need to meet certain legal status requirements to comply with U.S. export control laws and regulations.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. The Hardware organization develops AI-native silicon and system-level solutions for advanced AI workloads.