Senior DL Algorithms Engineer, Inference Performance

Nvidia

Confirmed live 2 days ago High trust

Remote

Quick summary

Work type: Remote
Location: Canada
Salary: $152,000–$241,500 / yr
Posted: 129 days ago
Freshness: Confirmed live 2 days ago

Market check

Salary context

Below market

How this pay compares to similar roles

Similar $226k

This role $197k

$136k most similar roles pay here $304k

This role pays less than 72% 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 DL Algorithms Engineer, Inference Performance

Role Posting Log in to save

As a Senior DL Algorithms Engineer - Inference Performance, you will join the team to optimize LLM and Omni model performance across the entire hardware and software stack. Your daily responsibilities include enabling state-of-the-art open models on accelerated inference stacks, contributing features and production code to frameworks like TRT-LLM, vLLM, SGLang, and FlashInfer. You will profile bottlenecks, perform competitive benchmarking, and co-design next-generation AI services. The role requires expertise in deep learning, neural networks, and GPU architecture. You must be proficient in PyTorch or similar high-performance computing frameworks while utilizing skills in performance profiling and analysis. Candidates should possess a strong understanding of computer architecture and algorithms, with preferred experience in CUDA or OpenCL programming to solve complex inference performance challenges within the domain of large language model and diffusion architectures.

Skills

Deep Learning LLM GPU Architecture PyTorch TRT-LLM vLLM SGLang FlashInfer CUDA OpenCL Performance Profiling HPC Neural Networks

What you'll do

Optimize state-of-the-art open models on NVIDIA’s accelerated inference software stack.
Develop new features and fix bugs in open-source frameworks like TRT-LLM, vLLM, and SGLang.
Profile and analyze performance bottlenecks across the entire inference stack to improve speed.
Benchmark state-of-the-art offerings and perform competitive analysis for NVIDIA’s software and hardware.
Co-design next-generation AI models and services with internal partner teams.
Implement optimizations across the full hardware/software stack from GPU architecture to deep learning frameworks.

What we're looking for

PhD in Computer Science, Electrical Engineering, CSEE, or equivalent experience.
At least 3 years of relevant professional experience.
Strong background in deep learning and neural networks, specifically regarding inference.
Experience with performance profiling, analysis, and optimization for GPU-based applications.
Proficiency in PyTorch or other frameworks for AI and HPC-heavy application development.
Deep understanding of computer architecture and fundamentals of GPU architecture.
Proven experience with processor and system-level performance optimization.
Strong fundamentals in algorithms and deep understanding of modern LLM/Diffusion architectures.