[Remote] Software Engineer, Hardware Enablement

Note: The job is a remote job and is open to candidates in USA. Modular is on a mission to revolutionize AI infrastructure by rebuilding the AI software stack. They are seeking a motivated engineer to join the Hardware Enablement team, where the primary focus will be on optimizing support for new hardware architectures and improving the Modular software stack.ResponsibilitiesImplement and validate support for new hardware architectures across the Modular stack, working under the guidance of senior engineers on the teamWrite and optimize Mojo kernels targeting novel accelerator architectures, with a focus on correctness first and performance iterationContribute to cross-team efforts improving portability infrastructure, tooling, and debugging workflows for new target hardwareCollaborate with hardware vendor engineers to understand target platforms, build integration tests, and triage platform-specific issuesDevelop working knowledge of new hardware platforms — including ISA documentation, memory hierarchies, and vendor toolchains — and share findings with the team through demos and write-upsParticipate in company events such as on-sites and hackathons, contributing to a collaborative and open engineering cultureSkills5+ years of experience in high-performance computing, compiler engineering, or related domains in industry or researchFamiliarity 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 systemsHands-on experience with at least one heterogeneous programming model (CUDA, SYCL, OpenCL, or similar), either as a user or contributorSome exposure to non-GPU accelerator architectures (DSPs, NPUs, or other hardware accelerators) is a strong plusCuriosity and willingness to learn new hardware platforms quickly, comfortable reading architecture manuals and vendor documentationA collaborative, team-oriented attitude and alignment with our cultureExperience with GPU DSLs/DSELs such as Triton, CUTLASS, or CuTeFamiliarity with MLIR or LLVM compiler infrastructureExperience working directly with hardware vendor teams or on platform bring-up effortsExposure to model serving or inference optimization workflowsBenefitsPremier insurance plansUp to 5% 401k matchingFlexible paid time offStock optionsTeam Building EventsRegular team onsites and local meetups in Los Altos, CA as well as different citiesTraveling 2-4 times a year is expected for all rolesCompany OverviewModular provides AI infrastructure for deployment, serving, and programming GPUs. It was founded in 2022, and is headquartered in Palo Alto, California, USA, with a workforce of 51-200 employees. Its website is https://www.modular.com.Company H1B SponsorshipModular has a track record of offering H1B sponsorships, with 3 in 2026, 10 in 2025, 6 in 2024, 8 in 2023, 4 in 2022. Please note that this does not guarantee sponsorship for this specific role.