AI Kernel Engineer

Majestic Labs ai; Los Altos (CA); Presencial; USD 140.000 - 210.000; Jornada completa

Descripción de la vacante

Majestic Labs is an AI startup building next-generation infrastructure for demanding AI workloads in the US. We design high-performance compute kernels and optimize for throughput and latency across heterogeneous units, collaborating with Triton and PyTorch teams.

You will prototype precision formats and contribute to hardware-software co-design. We value curiosity, collaboration, and relentless problem-solving.

Formación

• Degree in CS, computer engineering or related field.
• Strong background in parallel programming (CUDA/Triton/RISCV Vector/OpenMP).
• Deep understanding of memory layout, vectorization and cache behavior.
• Experience with wide-SIMD units and matrix/systolic engines.
• Familiarity with BLAS/BLIS and dense linear algebra.
• Experience with performance analysis and parallel debugging (GDB/Nsight).
• Hands-on profiling/optimizing compute/AI workloads (GEMM/softmax/attention).
• Proficiency in C++17+ with standard templates/algorithms.

Responsabilidades

• Design and implement high-performance compute kernels for AI primitives such as GEMM, attention, normalization, and convolution.
• Optimize for throughput, latency, and memory hierarchy across heterogeneous compute units (SIMD, matrix engines, DMA).
• Collaborate with compiler and runtime teams to integrate kernels into Triton and PyTorch pipelines.
• Profile and tune kernels using tools like Perfetto, VTune, Nsight, or custom simulators.
• Prototype and evaluate precision formats (FP16/BF16/FP8/e5m2, MXFP/FP4, etc.).
• Contribute to micro-architecture feedback loops, helping co-design ISA and memory features with the hardware team.

Conocimientos

CUDA

Triton

RISC-V Vector

OpenMP

GEMM

Educación

CS degree

Herramientas

Nsight

GDB

LLVM/MLIR

Descripción del empleo

We’re a fast-moving, US-Israeli AI startup building next-generation infrastructure for the world’s most demanding AI workloads. Our mission is to accelerate the future of intelligence and make it ubiquitously accessible by delivering full stack custom AI servers optimized for large-scale inference and training.

Backed by top-tier investors and led by industry veterans, we’re scaling rapidly. We seek forward-thinking engineers and operators who thrive in a collaborative environment and excel at solving complex challenges from first principles. If you want to build infrastructure that fundamentally changes what the world can accomplish with AI, come join us!

About The Position

• Design and implement high-performance compute kernels for AI primitives such as GEMM, attention, normalization, and convolution.
• Optimize for throughput, latency, and memory hierarchy across heterogeneous compute units (SIMD, matrix engines, DMA).
• Collaborate with compiler and runtime teams to integrate kernels into Triton and PyTorch pipelines.
• Profile and tune kernels using tools like Perfetto, VTune, Tracy, Nsight, or custom simulators.
• Prototype and evaluate precision formats (FP16/BF16/FP8/e5m2, MXFP/FP4, etc.).
• Contribute to micro-architecture feedback loops, helping co-design ISA and memory features with the hardware team.

Requirements

• Degree at any level in Computer Science, Computer Engineering, or a related field from a recognized university.
• Strong background in parallel programming (CUDA, Triton, RISC-V Vector (RVV), POSIX Threads, or OpenMP).
• Deep understanding of memory layout, vectorization, thread/block scheduling, and cache behavior.
• Experience programming wide-SIMD vector units and matrix/systolic engines.
• Familiarity with the parallel-computing ecosystem and its high-performance libraries and
• primitives, such as BLAS/BLIS, dense linear algebra, and parallel scan/reduce/sort.
• Skilled in performance analysis and parallel debugging using tools such as GNU Debugger and Nsight.
• Hands‑on experience profiling and optimizing compute or AI workloads (e.g., GEMM, softmax, attention).
• Solid grasp of numerical stability, precision formats, and mixed precision arithmetic.
• Proficiency in C++17 or higher, with strong knowledge of standard algorithms, data structures, and generic programming paradigms.
• Collaborative work style with the ability to operate effectively in multicultural, cross-disciplinary environments.

Preferred Qualifications

• Experience with optimization of irregular algorithms, such as graph computations or sparse
• numerical linear algebra, combining high-level data structure design with low-level SIMD and synchronization optimizations.
• Familiarity with LLVM/MLIR.
• RISC-V systems or bare-metal programming, including RISC-V vector and matrix extensions.

We seek smart, curious, self‑driven individuals who enjoy creative problem‑solving and continuous learning. Even if you don't meet all requirements, we'd love to hear from you if you have the mindset to tackle complex challenges.

Majestic Labs is an equal opportunity employer deeply committed to diversity of background and thought. If you are ready to dare greatly, learn from mistakes, engage in vigorous debates, and help create a step‑function shift in human technical capability, we want to meet you!