Join us as a Senior Deep Learning Software Engineer on our model optimization team to design and implement an automated inference and deployment solution. You will define a scalable architecture for deep learning inference, focusing on ease-of-use and compute efficiency across high-level frameworks like PyTorch and JAX, while also developing a high-performance execution environment with low-level GPU optimizations in CUDA or Triton. Your responsibilities include leveraging the torch 2.0 ecosystem to extract standardized model graph representations, optimizing inference techniques, collaborating with NVIDIA teams for kernel implementations, and analyzing GPU performance for continuous innovation. Ideal candidates have a strong background in deep learning, excellent software design skills, proficiency in Python and PyTorch, and experience with NVIDIA’s TensorRT SDKs and high-performance GPU kernels.
Define modular, scalable platform to bridge training and deployment workflows for deep learning models.
Analyze and extract standardized graph representation from PyTorch models for automated deployment solution.
Develop support for inference optimization techniques like speculative decoding and LoRA.
Collaborate with NVIDIA teams to integrate performant kernel implementations into automated deployment solutions.
Profile GPU kernel-level performance to identify hardware and software optimization opportunities.
Innovate continuously on inference performance to maintain market leadership in NVIDIA's inference software solutions.
What we're looking for
8+ years of experience in Deep Learning or equivalent education.
Strong proficiency in Python, PyTorch, and related ML tools.
Excellent software design skills including debugging and performance analysis.
Experience with GPU architecture and high-performance kernel development.
Contributions to open-source machine learning frameworks like PyTorch or JAX.
Knowledge of NVIDIA's deep learning SDKs such as TensorRT.
Familiarity with speculative decoding, LoRA, and inference optimization techniques.
Market check
Salary context
This
$224,000–$356,500
range sits above
99%
of similar postings on FindRole.
Peer median band
$152,000–$234,000
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$164,707–$235,750
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
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
801 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 797 roles with salary data.
Us, Ca, Santa Clara, US79 days ago
$224,000–$356,500
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