Ansys IDEAS Digital Forum Banner 1

Deep Learning Kernel Engineer

Deep Learning Kernel Engineer
by Daniel Nenni on 08-20-2020 at 5:47 pm


Job Description
Habana Labs is a young and innovative company focused on developing purpose-built AI processors, disruptive solutions that will shape the future of AI and Deep Learning computing. Habana was founded in 2016 by successful entrepreneurs, launched its first AI Inference processor in 2018, its Training processor in 2019 and was acquired by Intel in December 2019.  The company now operates as an autonomous subsidiary of Intel.  Our vision to take AI processing from its current limits to the peak of its potential continues. We see challenges as opportunities, laser focus on execution and are determined to fulfill our vision to improve the quality of life, work and leisure with our AI solutions. We are looking for exceptionally smart people who believe that AI will change the world and would like to join us on our exciting journey!


We are looking for a hands-on software engineer with strong mathematical foundation to join the Application Engineering team, with in-depth knowledge in AI software frameworks, performance engineering and data-science. Hands-on skills to root cause bugs and optimize for custom AI hardware and software are required.


Roles and Responsibilities:

Implementation of kernel methods that reflect computations in large, multi-layer neural networks
mapping of user-supplied Deep Learning networks to run on Habana AI HW accelerators for inference and training.
Profiling and optimization of both individual kernels as well as full network operation
Working in both pre and post silicon environments
Unit testing, numerical accuracy and performance verification of work
Additional Skills

Fast learner
Strong communication and interpersonal skills are required
Must be willing to work independently as well as with others in a fast paced highly technical environment
Minimum Qualifications

– BS in Engineering, Information Systems, Computer Science with 6+ years of experience  or related field or MS degree with 4+ years of experience in Engineering, Information Systems, Computer Science, or related field

– 4+ years of hands-on coding experience in C++11 programming language and extensive knowledge of modern language features

– 3+ years of experience in Numerical coding experience in C++

– 3+ years of experience in commercial quality system software, e.g. compilers, debuggers, profilers

– 3+ years of Experience with compute kernel development

– 3+ years of Experience with all modern compiler toolchains including front and back ends

– 1+ years of experience in Deep Learning frameworks and theory (TF, Caffe, PyTorch, OpenCV, etc.)

– 1+ years of experience in a Linux environment

Preferred Qualifications

– 1+ years of direct deep learning implementation experience

– 2+ years of Parallel programming, especially design of GPU accelerated kernels

– 2+ years of Python and scientific computing experience

– 2+ years of Linear algebra and mathematical optimization techniques

Inside this Business Group
Intel AI, leveraging Intel’s world leading position in silicon innovation and proven history in creating the compute standards that power our world, is transforming Artificial Intelligence (AI) with the Intel AI products portfolio. Harnessing silicon designed specifically for AI, end to end solutions that broadly span from the data center to the edge, and tools that enable customers to quickly deploy and scale up, Intel AI is inside AI and leading the next evolution of compute.

Other Locations

US, California, Santa Clara;US, Oregon, Hillsboro

Apply for job

To view the job application please visit