Wafer AI - Member of Technical Staff
decircleMillbrae, CA
Wafer AI - Member of Technical Staff
L6
decircleMillbrae, CAtoday
Occupations
Software DevelopersComputer and Information Research ScientistsComputer Systems Engineers/ArchitectsIndustries
Computing Infrastructure Providers, Data Processing, Web Hosting, and Related ServicesComputer Systems Design ServicesSoftware PublishersWafer AI: maximize intelligence per watt; autonomous AI performance engineers optimizing inference on heterogeneous hardware. 7 people, $4M raised, SF.Comp: $200K-$300K + 0.5%-1% equity.
Location: on-site 5 days FiDi SF.
Visa: Visa transfers (H-1B transfer, OPT); must already be in US; no new H1B.
Responsibilities:
Ship day-zero support for new open-source models tuned for latency/throughputOptimize serving stack: batching, KV cache, speculative decoding, quantizationWrite/tune kernels in CUDA, HIP, Triton for NVIDIA, AMD, TPU, Trainium, D-MatrixDesign, deploy, operate heterogeneous multi-vendor clustersRun production inference: reliability, observability, cost per tokenTech stack: CUDA, HIP, Triton, Python, TPU, AWS TrainiumSource: https://www.paraform.com/share/wafer-ai/cmrtyva4m000j0cl7i7j9wbue1-6 yrs SWE focused on systems close to hardwareGPU kernels (CUDA/HIP/Triton), inference serving optimizationFirst-principles, resourceful, high EQ; customer-facing comfortOn-site 5 days SF; must be in US
Apply now (opens in a new tab)
Level
LeadL6
Location
Millbrae, CA
Occupation
Software Developers
Industry
Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services
Posted
today
To get sharper similar jobs, create your profile using the link below.