Part of the small (but exciting!) team responsible for our NMAX –a highly efficient AI neural-network (NN) inferencing chip:
-Linux kernel device driver development interfacing with our NMAX hardware.
-Communicate via common interfaces such as PCI-Express, USB, etc.
-DMA and other techniques for efficient high
-speed communication, including knowledge of scattered buffer, zero-copy, virtual memory, etc.
-Efficient handling of interrupts and memory management
-Work closely with architects and hardware developers to develop and debug device driver and NMAX software (NMAX Compiler).
-Support work for our NMAX software for automatic mapping of NN models from TensorFlow, controlling NMAX engines for highly efficient neural-network (NN) inference
EXPERIENCE AND SKILL REQUIRED
BSEE/MSEE with 3 years of relevant industry experience in software driver development
Must be very smart and very motivated
Must have hands-on experience developing Linux kernel device drivers
Detailed knowledge about common communication buses and interfaces such PCI-E, USB
Hands-on experience with DMA controllers & interrupt controllers
Knowledge of Intel/ARMCPU Architecture, memory management and interrupt handling
Preferred experience OR willing to quickly learn:
-Experience in bringing up new hardware platforms from scratch
-Experience with interfacing devices such as network cards, storage controllers, graphics cards, etc.
-Proficient in performance profiling, tuning, and debugging of performance in kernel space
Must be passionate about being part of an aggressive, venture-backed startup team that is changing the way chips are architected, designed, and programmed
Must be entrepreneurial, innovative problem solver and willing to work hard.
MUST live in Silicon Valley and have US citizenship or US permanent residency (“green card”).