As a Software Engineer at NVIDIA’s Omniverse NuRec SDK team, you will play a pivotal role in advancing the integration of cutting-edge 3D Vision Language Models into production environments. Your daily tasks include designing and optimizing containerized inference execution for state-of-the-art models, developing benchmarks to ensure accuracy and performance, and maintaining these systems throughout their lifecycle. You will also contribute features related to VLMs to open-source projects like vLLM while collaborating closely with research and product teams. Ideal candidates have a strong background in building distributed AI systems using Docker, Kubernetes, and modern inference platforms such as vLLM, Torch, and TRT-LLM, along with proficiency in Python and C++. Additionally, experience in 3D graphics, neural reconstruction, and low-level ML model optimization is highly valued.
Skills
Python
C++
Kubernetes
Docker
vLLM
Torch
TRT
TRT-LLM
Helm
REST
gRPC
CI/CD
CUDA
PostgreSQL
Git
3D_computer_vision
Neural_reconstruction
Gaussian_Splatting
What you'll do
Design and optimize containerized inference execution for NVIDIA's latest 3D VLMs.
Develop benchmarks to validate models' accuracy and performance metrics.
Release and maintain production-grade AI systems throughout their lifecycle.
Contribute VLM-related features to open-source projects like vLLM.
Collaborate with Research and Product teams to influence common roadmaps.
What we're looking for
Master’s in Computer Science/Electrical Engineering with relevant experience.
Expertise in building, validating, and releasing production-grade AI distributed systems.
Deep knowledge of Docker, Kubernetes, REST, gRPC, Helm for distributed applications.
Hands-on experience with modern inference platforms like vLLM, Torch, TRT.
Proficiency in Python and C++ with strong software engineering fundamentals.
Track record of contributing to open-source projects or production-grade software.
Experience in ML model engineering including training, fine-tuning, distillation.
Market check
Salary context
Competitive pay
How this pay compares to similar roles
Similar $205k
This role $197k
$141k
most similar roles pay here
$252k
This role pays less than
52%
of similar roles. Most pay
$174,050–$235,750
— the shaded band above.
At the midpoint, this role pays about
$197k
versus about
$205k
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
824 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 812 roles with salary data.
CUDA
TensorRT
TVM
MLIR
XLA
Python
C/C++
QNX
Linux
GPU
Deep Learning
Transformer Models
Vision-Language Models
Diffusion Models
State Space Models
Parallel Programming
Memory Management
Embedded Systems
CI/CD
MLPerf