"fp8" Jobs

12 open tech roles matching “fp8”, taken straight from company career pages — not reposted from other job boards. Most in demand right now: GPU, CUDA, vLLM. Every listing is re-checked daily and closed roles are removed.

Showing 12 of 12 results

Member of Technical Staff, TPU Performance Engineering Visa

Join Inferact as a TPU performance engineer to optimize vLLM for Google TPUs, enhancing AI inference performance.

Inferact Singapore S$200k–S$400k/yr Published 4 months ago

JAX vLLM ML Pallas TPU

Flexible on stack

Apply →

Member of Technical Staff, TPU Performance Engineering Hybrid Visa

Join Inferact as a TPU performance engineer to optimize vLLM for Google TPUs, enhancing AI inference performance.

Inferact San Francisco $200k–$400k/yr Published 4 months ago

JAX vLLM ML Pallas TPU

Flexible on stack

Apply →

Member of Technical Staff, Kernel Engineering Visa

Join Inferact as a performance engineer to optimize vLLM, the fastest AI inference engine, working directly with hardware vendors.

Inferact Singapore S$200k–S$400k/yr Published 4 months ago

C++ FlashAttention CUDA LLVM rocprof

Flexible on stack

Apply →

Software Engineer - GPU Kernels

Join Baseten as a GPU Kernel Engineer to optimize high-performance GPU kernels for cutting-edge AI applications.

baseten San Francisco Published 1 year ago

C++ Nsight Systems Torch Profiler CUDA Machine Learning

Flexible on stack 70% coding

Apply →

Member of Technical Staff, Kernel Engineering Hybrid Visa

Join Inferact as a performance engineer to optimize vLLM, the fastest AI inference engine, working with cutting-edge hardware.

Inferact San Francisco $200k–$400k/yr Published 9 months ago

C++ CUDA LLVM ML MLIR

Flexible on stack

Apply →

Member of Technical Staff, AMD GPU Performance Engineering Visa

Join Inferact as an AMD GPU performance engineer to optimize vLLM for the AMD accelerator ecosystem.

Inferact Singapore S$200k–S$400k/yr Published 4 months ago

Triton AMD vLLM CK GPU

Flexible on stack

Apply →

Software Engineer - Inference Performance

Join Baseten as a Software Engineer to optimize AI inference performance in a fast-paced startup environment.

baseten San Francisco Published 1 month ago

C++ TensorRT-LLM TensorRT PyTorch Python

Flexible on stack

Apply →

ML Engineer (Training Infra), Foundational Models

Own the infrastructure for training foundational models at Sarvam AI, focusing on distributed training and optimization.

Sarvam AI Bengaluru Published 4 weeks ago

Triton CUDA DeepSpeed Slurm Megatron-LM

Flexible on stack

Apply →

Member of Technical Staff, AMD GPU Performance Engineering Hybrid Visa

Join Inferact as an AMD GPU performance engineer to optimize vLLM for the AMD accelerator ecosystem.

Inferact San Francisco $200k–$400k/yr Published 4 months ago

Triton AMD vLLM CK GPU

Flexible on stack

Apply →

ML Researcher - Image / Video Diffusion Visa

Join Krea as an ML Researcher to train diffusion models for image and video generation in a creative AI-focused environment.

krea.ai San Francisco Published 2 months ago

FP8 EP MXFP8 CP NVFP4

Flexible on stack

Apply →

Staff Software Engineer, Inference

Join CoreWeave as a Staff Software Engineer to lead the development of a Kubernetes-native inference platform for AI workloads.

Coreweave Sunnyvale, CA / Bellevue, WA $188k–$275k/yr Published 6 months ago

C++ TensorRT-LLM Triton TorchServe CUDA

Flexible on stack

Apply →

ML Researcher - Posttraining Visa

Join Krea as an ML Researcher to finetune diffusion models and enhance AI creative tools in a collaborative environment.

krea.ai San Francisco Published 2 months ago

VLM Diffusion Models reinforcement learning PyTorch LLM

Flexible on stack

Apply →