Note: The job is a remote job and is open to candidates in USA. Modular is a company focused on building the next generation AI platform to enhance the deployment of AI models. They are seeking a Software Engineer for the Hardware Enablement team to optimize support for new hardware architectures and collaborate with internal and external partners.
Responsibilities
- Implement and validate support for new hardware architectures across the Modular stack, working under the guidance of senior engineers on the team
- Write and optimize Mojo kernels targeting novel accelerator architectures, with a focus on correctness first and performance iteration
- Contribute to cross-team efforts improving portability infrastructure, tooling, and debugging workflows for new target hardware
- Collaborate with hardware vendor engineers to understand target platforms, build integration tests, and triage platform-specific issues
- Develop working knowledge of new hardware platforms — including ISA documentation, memory hierarchies, and vendor toolchains — and share findings with the team through demos and write-ups
- Participate in company events such as on-sites and hackathons, contributing to a collaborative and open engineering culture
Skills
- 5+ years of experience in high-performance computing, compiler engineering, or related domains in industry or research
- Familiarity with how AI operators are implemented at a low level (e.g., experience writing or modifying GPU kernels, custom operators, or working with frameworks like PyTorch at the C++ layer)
- Proficiency in C++ and experience working in complex, multi-component software systems
- Hands-on experience with at least one heterogeneous programming model (CUDA, SYCL, OpenCL, or similar), either as a user or contributor
- Some exposure to non-GPU accelerator architectures (DSPs, NPUs, or other hardware accelerators) is a strong plus
- Curiosity and willingness to learn new hardware platforms quickly, comfortable reading architecture manuals and vendor documentation
- A collaborative, team-oriented attitude and alignment with our culture
- Experience with GPU DSLs/DSELs such as Triton, CUTLASS, or CuTe
- Familiarity with MLIR or LLVM compiler infrastructure
- Experience working directly with hardware vendor teams or on platform bring-up efforts
- Exposure to model serving or inference optimization workflows
Benefits
- Premier insurance plans
- Up to 5% 401k matching
- Flexible paid time off
- Stock options
- Team Building Events
- We organize regular team onsites and local meetups in Los Altos, CA as well as different cities. Traveling 2-4 times a year is expected for all roles.
Company Overview
Company H1B Sponsorship