Senior Deep Learning Software Engineer, Inference

Nvidia

Confirmed live 2 days ago High trust

Remote

Quick summary

Work type: Remote
Location: CATXNYWAMA
Salary: $152,000–$241,500 / yr
Posted: 15 days ago
Freshness: Confirmed live 2 days ago
Nearby: 49 roles within 25 mi

Market check

Salary context

Below market

How this pay compares to similar roles

Similar $226k

This role $197k

$137k most similar roles pay here $293k

This role pays less than 71% of similar roles. Most pay $196,750–$254,750 — the shaded band above. At the midpoint, this role pays about $197k versus about $226k for comparable roles.

Based on 240 similar postings.

Employer

About Nvidia

Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing

Nvidia currently has 896 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 876 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Senior Deep Learning Software Engineer, Inference

Role Posting Log in to save

As a Senior Deep Learning Software Engineer, Inference, you will join the team responsible for developing and maintaining high-performance open-source frameworks for large-scale model serving. You will design, build, and optimize GPU-accelerated software to facilitate the deployment of groundbreaking language models. Your daily work involves performance optimization, analysis, and tuning of deep learning models across various domains including LLM, Multimodal, and Generative AI. You will contribute code to inference libraries such as vLLM, SGLang, and FlashInfer while implementing algorithms for public release. The role requires expert C/C++ programming skills and experience with Python. You will utilize tools like CUTLASS, OAI Triton, NCCL, and CUDA kernels to optimize model serving pipelines across datacenter GPUs and edge SoCs. Your work addresses the technical challenge of scaling performance for state-of-the-art models across diverse hardware architectures.

Skills

CUDA C++ Python PyTorch vLLM SGLang Triton CUTLASS NCCL NVSHMEM Deep Learning LLM Generative AI GPU Programming Performance Optimization Profiling Agile

What you'll do

Design and optimize GPU-accelerated software for large-scale model serving and inference.
Perform performance optimization, analysis, and tuning of LLM, Multimodal, and Generative AI models.
Scale the performance of deep learning models across various NVIDIA accelerator architectures.
Contribute features and code to inference libraries such as vLLM, SGLang, and FlashInfer.
Implement and optimize model serving pipelines using CUTLASS, OAI Triton, NCCL, and CUDA kernels.
Integrate the latest algorithms from the deep learning community into public inference frameworks.
Identify and drive performance improvements for state-of-the-art models across datacenter GPUs and edge SoCs.

What we're looking for

Master's or PhD degree in Computer Engineering, Computer Science, EECS, or a related field.
At least 5 years of relevant software development experience.
Excellent C/C++ programming and software design skills.
Experience with GPU programming using CUDA, OAI Triton, or CUTLASS.
Experience with multi-GPU communications such as NCCL or NVSHMEM.
Proficiency in Python is preferred.
Experience deploying or optimizing the inference of deep learning models in production is a plus.
Background in performance modeling, profiling, debugging, and code optimization is a plus.

Save