Kernel Engineer, Modular
$166.5-242k
The estimated base salary range for this role to be performed in Canada, regardless of the province, is $157,500.00 - $228,500.00 CAD. The total compensation for a candidate will also include annual target bonus, equity, and benefits, with equity making up a significant portion of your total compensation
AI infrastructure for developers
Open for applications
AI infrastructure for developers
201-500 employees
Open for applications
$166.5-242k
The estimated base salary range for this role to be performed in Canada, regardless of the province, is $157,500.00 - $228,500.00 CAD. The total compensation for a candidate will also include annual target bonus, equity, and benefits, with equity making up a significant portion of your total compensation
201-500 employees
Company mission
To have real, positive impact in the world by reinventing the way AI technology is developed and deployed into production with a next-generation developer platform.
Role
Who you are
- In-depth knowledge of C++ and low-level (micro)architectural performance is required
- 4+ years of experience working on complex code and systems
- Experience with performance modeling and performance data analysis
- Understanding of Parallelization techniques for ML / HPC Acceleration
- Deep interest in machine learning technologies and use cases
- Creativity and curiosity for solving complex problems, a team-oriented attitude that enables you to work well with others, and alignment with our culture
Desirable
- Some knowledge of compiler fundamentals is valuable, as is familiarity with kernel authoring paradigms (i.e., OpenMP, CUDA, Halide, Rise/Lift, or others)
- Experience with performance profilers, performance data analysis tools, visualization tools, and debugging or experience working with embedded systems
- Experience working with distributed/parallel programming models and an understanding of parallel hardware
- Experience developing firmware for accelerators and embedded programming
- Experience with HPC programming and accelerator languages such as CUDA, OpenCL, SYCL, etc
What the job involves
- ML developers today face significant friction in taking trained models into deployment
- They work in a highly fragmented space, with incomplete and patchwork solutions that require significant performance tuning and non-generalizable/ model-specific enhancements
- At Modular, we are building the next generation AI platform that will radically improve the way developers build and deploy AI models
- A core part of this offering is providing a platform that allows developers reuse deployment specific tuning and enhancements across model families and frameworks
- As an AI Kernel Engineer you will own developing and tuning performance libraries for AI models
- You will develop kernels and algorithms to increase performance of kernels, reduce the activation volumes, speedup data pre- and post-processing, and in general increase the end-to-end performance of the model
- Design and optimize high-performance ML numeric and data manipulation kernels/operators
- Utilize low-level C/C++/Assembly programming to achieve state of the art performance. Your work will also entail potentially introducing new novel compiler and tools support
- Work with compiler, framework, runtime and performance teams to deliver end-to-end performance that fully utilizes today’s complex server and mobile systems
- Collaborate with architects and hardware engineers to co-design future accelerators, including ISA for new hardware features and evolving ISA
- Collaborate with machine learning researchers to guide system development for future ML trends
Share this job
View 2 more jobs at Modular
Company
Company benefits
- Leading medical, dental and vision packages
- Equity packages
- Generous maternity & paternity leave
- 401K Plan
- Work wherever you want
- Unlimited Vacation & PTO
- Corporate perks & epic team fun
- Great set up
Funding (2 rounds)
Aug 2023
$100m
LATE VC
Jun 2022
$30m
EARLY VC
Total funding: $130m
Our take
Modular has been developing a programming language optimized for developing AI software, to make it easier for developers to complete their AI projects faster and more effectively.
Most of the time, developers will write AI models in Python because of its relatively simple and concise syntax. However, with this simplicity comes performance issues that can slow down programs and code, a problem that Modular hopes to address.
The company's language, named Mojo, combines the usability of Python with the performance of C; which, the company says, brings unparalleled programmability of AI hardware and extensibility of AI models.
With significant funding at its back, the company plans to enhance Mojo moving forward, as well as invest in its other product - a software tool called AI Engine that is designed to make companies’ neural networks faster.
Kirsty
Company Specialist at Welcome to the Jungle