Kernel Engineer
San Francisco, CA
We are a small team with a shared belief in the future of Intelligence. At Verterra, you won't just be working on Intelligence — you'll be helping define its future.
About the role
We are looking for a Kernel Engineer to join our team. You will develop and implement new kernels to accelerate our AI models.
What you'll work on
- Design & optimize ultra-high-throughput GPU compute kernels in CUDA, HIP/rOCm and Vulkan compute that power our Synthetic Reality Engine and world-model training pipeline
- Extend and maintain Emma, our proprietary cross-platform kernel language, including its SPIR-V and CUDA back-ends and autotuning tool-chain
- Implement fused tensor operators, memory orchestration, warp-level primitives and tensor graph computations that already make our training 10x faster and 40x cheaper than incumbent stacks
- Profile, benchmark and squeeze every FLOP from NVIDIA and AMD GPUs across single-node to multi-thousand GPU clusters; upstream critical patches to open-source drivers where needed
- Partner with Research to translate new model architectures into production-ready kernels within hours or days, not weeks or months
What we're looking for
- 5+ years writing performance-critical GPU code; mastery of CUDA, HIP and ideally Vulkan compute pipelines
- Deep knowledge of GPU memory hierarchies, synchronization, occupancy tuning and compiler internals; you think in warps and wavefronts
- Fluency in modern C++ and Python; experience building DSLs, codegen or MLIR/LLVM passes is a huge plus
- Experience with large-scale distributed computing, multi-GPU and multi-node systems; comfortable with MPI, UCX and/or NCCL
- Proven track record shipping kernels used at scale (DL frameworks, rendering engines, scientific HPC or similar)
- Comfortable navigating ambiguous, fast-moving startup environments and collaborating across research, product and hardware teams
- We hire for ability, not credentials — if you're obsessed with pushing silicon to its limits and shaping the future of intelligence, we want to hear from you
Compensation, benefits, and perks
- Annual salary: $245K - $445K
- 401(k) plan with 6% salary matching
- Generous health, dental and vision insurance for you and your dependents
- Unlimited paid time off
- Visa sponsorship and relocation stipend to bring you to SF, if possible
- A small, fast-paced, highly focused team