Qualifications
Key Responsibilities:Contribute to the productization of our software stack for the AI compute engine. Develop, enhance, and maintain software kernels for next-generation AI hardware. Leverage your expertise in building software kernels tailored for diverse hardware architectures. Map AI framework-generated computational graphs to underlying architectures effectively. Collaborate with compiler experts and other software/hardware teams to optimize and scale software deliverables within tight timelines. Required Qualifications:MS or PhD in Computer Engineering, Mathematics, Physics, or a related field with over 10 years of industry experience. Deep understanding of computer architecture, data structures, system software, and machine learning principles. Proficient in C/C++ and Python within a Linux environment using standard development tools. Experience in implementing algorithms in high-level languages, particularly for specialized hardware such as FPGAs, DSPs, GPUs, and AI accelerators using libraries like CuDA.
About the job
Join d-Matrix, where we are at the cutting edge of generative AI, revolutionizing technology through innovative software and hardware solutions. Our ethos is rooted in collaboration and respect, fostering an environment where diverse perspectives lead to exceptional outcomes.
We value humility and prioritize open, direct communication. If you are passionate about overcoming challenges and thrive in a fast-paced environment, we invite you to explore the countless possibilities with us. Together, let’s redefine the future of AI.
Work Arrangement: Hybrid, requiring onsite presence at our Santa Clara, CA headquarters three days a week.
About d-Matrix
At d-Matrix, we are pioneering the integration of generative AI into transformative technology, striving to redefine what’s possible in the realm of software and hardware innovation. We cultivate a culture that emphasizes respect, collaboration, and inclusivity, driving us to create groundbreaking solutions in AI.