KERNEL ENGINEER

MakerMaker

San Francisco, CA

On-site

Who this role is best for

Systems engineers with GPU kernel optimization experience will find this performance-critical role in a small team focused on machine learning workloads. The job emphasizes low-level hardware fluency and end-to-end impact in a San Francisco-based, full-time setting.

Best fit for

Candidates with 4+ years of hands-on GPU kernel optimization and a track record of measurable system improvements
— “4+ years writing performant GPU kernels ... track record of shipping kernel-level optimizations that moved a measurable metric in a real system”
Individuals comfortable working across multiple kernel frameworks and collaborating closely with research teams
— “Co-design kernels with the research teams ... when the kernel and the algorithm need to change together, you participate in both”
Engineers who can bridge the gap between theoretical algorithm design and practical hardware performance
— “the gap between 'this works' and 'this is fast on the hardware we have' is enormous, and that gap directly bounds what our researchers can try”

Things to consider

This role requires on-site presence in San Francisco despite being a small team
— “We're a small, well-funded team that works onsite in San Francisco”
The position demands a broad skill set across multiple kernel frameworks and hardware architectures
— “We expect breadth across the kernel surface our models actually use”

How to stand out

Highlight end-to-end performance improvements and specific kernel optimizations in your resume and interview stories
— “track record of shipping kernel-level optimizations that moved a measurable metric in a real system”
Demonstrate fluency in profiling tools and hardware-level analysis in your application materials
— “Profile real workloads with hardware counters and translate findings into specific kernel-level optimizations”
Emphasize experience integrating optimized kernels into training and serving stacks
— “Integrate optimized kernels into our training and serving stacks; benchmark before and after; verify the win is real end-to-end”
Include open-source contributions to kernel-related projects if applicable
— “Open-source contributions to kernel libraries, compilers, or ML frameworks”

Pace · SteadyCollaboration · MediumAutonomy · HighDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

Writes and optimizes GPU kernels for training and inference
Profiles real workloads and translates findings into specific kernel-level optimizations
Integrates optimized kernels into training and serving stacks
Maintains kernel quality over time

Typical background

4+ years writing performant GPU kernels

Skills & requirements

Required

GPU Kernel OptimizationCUDARocmTritonPerformance CountersMemory HierarchyOccupancyRegister PressureTensor CoresWarp SchedulingProfilingHardware-level FluencySystems ExpertiseFramework-level Python And C++

Preferred

Open-source ContributionsMultiple Accelerator ArchitecturesCollective Communication PrimitivesCompiler Or Runtime Background

Stack & domain

CUDARocmTritonNsightNcuPythonC++GPU KernelsPerformance OptimizationMachine Learning

About the role

Original posting from MakerMaker via Ashby

ABOUT THE COMPANY
We're building autonomous research agents for recursive self-improvement (multi-agent systems that propose, run, and analyze machine learning experiments). We're a small, well-funded team that works onsite in San Francisco.
ABOUT THE ROLE
You'll write and optimize the GPU kernels and supporting systems software that makes our training and inference workloads fast. This is deep, low-level work (performance counters, memory bandwidth, warp-level scheduling) applied to the specific shapes and patterns our models actually use.
We hire kernel engineers because the gap between "this works" and "this is fast on the hardware we have" is enormous, and that gap directly bounds what our researchers can try. You'll close that gap.
WHAT YOU'LL DO
Write and optimize GPU kernels (CUDA, ROCm, Triton, or similar) for training and inference workloads: attention variants, MoE layers, custom activations, communication primitives
Profile real workloads with hardware counters and translate findings into specific kernel-level optimizations
Co-design kernels with the research teams, when the kernel and the algorithm need to change together, you participate in both
Integrate optimized kernels into our training and serving stacks; benchmark before and after; verify the win is real end-to-end
Maintain kernel quality over time as hardware, frameworks, and workloads shift underneath
Spread kernel-level fluency across the team; we want this expertise shared, not siloed
WHAT WE'RE LOOKING FOR
4+ years writing performant GPU kernels (CUDA, ROCm, Triton, or production-grade equivalent)
Hardware-level fluency: memory hierarchy, occupancy, register pressure, tensor cores, warp scheduling
Profiling fluency (Nsight, ncu, or comparable tools) and the discipline to measure before changing
Track record of shipping kernel-level optimizations that moved a measurable metric in a real system
Strong systems expertise: you understand how kernels live inside larger frameworks and how integration choices affect end-to-end performance
Comfortable reading framework-level Python and C++ around your kernels
NICE TO HAVE
Open-source contributions to kernel libraries, compilers, or ML frameworks
Experience with multiple accelerator architectures (different GPU families, TPUs, custom ASICs), preferably AMD GPUs
Familiarity with collective communication primitives (NCCL or equivalent)
Compiler or runtime background
THIS ROLE IS PROBABLY NOT FOR YOU IF
You haven't gotten your hands dirty at the kernel level: this isn't a higher-level systems role rebranded
You want to stay narrowly in one library; we expect breadth across the kernel surface our models actually use
Performance work without measurable end-to-end impact frustrates you

Source: MakerMaker careers (Ashby)