GPU Kernel Engineering Manager, Modular
$261-363k
+ Stock options
Fast, scalable Gen AI inference platform
Open for applications
Fast, scalable Gen AI inference platform
201-500 employees
Open for applications
$261-363k
+ Stock options
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
- 7+ years of experience in people management
- 15+ years of experience in the field of high performance programming, performance analysis, and related areas
- Deep understanding of GPU computer architecture (memory hierarchies, tensor-cores, etc.) and their impact on algorithm design
- Self motivation with the ability to design, communicate and lead new projects
- Experience with GPU programming languages such as CUDA or OpenCL
- Familiarity with GPU assembly such as PTX and SASS
- Knowledge of SOTA frameworks such as CUTLASS, TRTLLM, Triton, etc
- Able to identify industry trends, analyze emerging technologies and disruptive paradigms
- Creativity and curiosity for solving complex problems, a team-oriented attitude that enables you to work well with others, and alignment with our culture
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
- This role focuses on providing customers with a platform that delivers state-of-the-art performance across various model families and use cases
- As the MAX Kernels team leader, you will oversee engineers who specialize in cutting-edge GPU kernels to accelerate Modular’s MAX platform
- Lead and scale the Kernel team responsible for developing cutting-edge AI algorithms and compute building blocks for the MAX platform across various GPU hardware
- Drive the development and optimization of kernels and algorithms to deliver top-tier performance and accuracy across the entire GenAI inference solution stack
- Collaborate with other teams to analyze and optimize AI performance on diverse GPU architectures throughout the stack
- Provide technical leadership by implementing new optimization approaches and staying current with the latest advancements in hardware and algorithms
- Make critical architectural decisions that impact the entire platform and guide the technical direction of the team
- Mentor team members and others within the company, fostering both personal and team development at the forefront of technology
- Establish and maintain deep technical expertise within the team while managing shifting priorities in a fast-paced environment
- Cultivate high-performing team culture and foster collaboration across the entire engineering organization
Our take
AI development is booming, but the tools behind it? Not so much. Developers are often stuck dealing with messy, disconnected systems that slow everything down and bump up costs.
To address this, Modular has developed a unified AI platform that streamlines the development process. It's AI Engine enhances the performance of models on CPUs and GPUs, supporting popular frameworks like TensorFlow and PyTorch. And on top of that, it's built Mojo, a programming language that's as easy as Python but much faster (35,000 times faster).
In 2023, the company raised an impressive $100M to power its mission. It's been using this funding to grow its team, support more hardware, and push Mojo even further. With the hopes of making AI development faster, smoother, and a whole lot more fun for everyone.
Kirsty
Company Specialist at Welcome to the Jungle
Company
Funding (2 rounds)
Aug 2023
$100m
LATE VC
Jun 2022
$30m
EARLY VC
Total funding: $130m
Company benefits
- A variety of fantastic health benefits (health, dental, vision insurance; life insurance etc) are available
- A 401k plan with up to 5% match
- Free tax advice on Carta
- Generous work-from-home stipend of $1500 to help you improve your home office
- Unlimited paid time off and flexible work hours
Leadership
Chris Lattner
(Co-Founder & CEO)Founder, Architect, Engineer and BDFL for the LLVM Organization. Former President of Engineering and Product at SiFive, as well as working in various roles at Google, Tesla, and Apple.
Tim Davis
(Co-Founder & President)Worked at Google for 5 years, ultimately as Group Product Lead for Google ML. Previously founded Fluc Inc, where they developed the entire ML powered delivery system with their co-founder, and mapping software system CrowdSend.
Salary benchmarks
We don't have enough data yet to provide salary benchmarks for this role.
Submit your salary to help other candidates with crowdsourced salary estimates.
Share this job
View 7 more jobs at Modular