"flashattention" Jobs

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

Showing 5 of 5 results

LLM Inference Frameworks and Optimization Engineer

Together AI San Francisco, Singapore, Amsterdam $160k–$230k/yr Published 1 year ago

C++ TensorRT-LLM SGLang CUDA vLLM

Apply →

Senior ML Research Scientist, Pegasus Hybrid

Drive research on Pegasus's complex problems in a hybrid role at a growing AI company focused on video understanding.

Twelve Labs Seoul, South Korea Published 5 months ago

Vision-Language Systems Machine Learning PyTorch Python Multimodal LLMs

Flexible on stack

Apply →

Staff ML Research Engineer, Pegasus - Training Performance Hybrid

Drive technical direction for training infrastructure and operations within Pegasus at a growing AI company focused on video understanding.

Twelve Labs Seoul, South Korea Published 1 week ago

video processing Machine Learning AI/ML distributed systems data processing

Apply →

Senior Machine Learning Engineer, Pegasus Hybrid

Build and operate production ML systems for Pegasus, focusing on reliability and performance in a hybrid work environment.

Twelve Labs Seoul, South Korea Published 3 weeks ago

Machine Learning Video Language Models multimodal data Kubernetes

Flexible on stack

Apply →

Performance Engineer, Kernels Hybrid

Join Sarvam AI as a Senior Performance Engineer to optimize GPU kernels for high-performance ML systems.

Sarvam AI Bengaluru Published 1 month ago

DeepEP PTX FlashAttention CUDA Mooncake

Apply →