Senior Deep Learning Software Engineer, Inference

NVIDIA AI; Washington; Presencial; USD 140.000 - 230.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity

Comprehensive benefits package

Descripción de la vacante

NVIDIA AI in Washington designs, builds, and optimizes GPU-accelerated software for high-performance deep learning inference and model serving.

This role focuses on improving performance for LLM and Generative AI models across NVIDIA accelerators using open-source frameworks, requiring advanced C/C++ skills, GPU programming, and DL optimization expertise.

Formación

• Requires a Master's or PhD in a relevant field and over 5 years of software development experience with strong C/C++ skills.
• Experience with GPU programming, DL model optimization, and performance profiling is highly desired.

Responsabilidades

• Design, build, and optimize GPU-accelerated software for high-performance deep learning inference and model serving.
• Focus on improving performance for LLM and Generative AI models across NVIDIA accelerators using open-source frameworks.

Conocimientos

C++

Python

CUDA

Deep Learning Inference

LLM Optimization

Generative AI

OAI Triton

CUTLASS

NCCL

vLLM

SGLang

FlashInfer

Software Design

Performance Profiling

GPU Programming

Agile

Educación

Master's or PhD in a relevant field

Herramientas

OAI Triton

CUTLASS

NCCL

vLLM

SGLang

FlashInfer

Descripción del empleo

Design, build, and optimize GPU-accelerated software for high-performance deep learning inference and model serving. Focus on improving performance for LLM and Generative AI models across NVIDIA accelerators using open-source frameworks.

Requirements

Requires a Master's or PhD in a relevant field and over 5 years of software development experience with strong C/C++ skills. Experience with GPU programming, DL model optimization, and performance profiling is highly desired.

Key Skills

C++, Python, CUDA, Deep Learning Inference, LLM Optimization, Generative AI, OAI Triton, CUTLASS, NCCL, vLLM, SGLang, FlashInfer, Software Design, Performance Profiling, GPU Programming, Agile

Benefits

Equity, Comprehensive benefits package