Principal LLM Inference Algorithms Engineer

NEPSE Trading; Northern (KY); Hybrid; USD 272,000 - 431,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA seeks outstanding engineers to advance LLM inference, optimizing agentic workloads and building scalable, datacenter-scale systems. You will contribute to performance-enhancing algorithms and protocols that push the boundaries of what's possible with large language models.

Required: advanced degrees and 15+ years in deep learning, strong Python/C++ skills, and deep knowledge of GPU/parallel computing. Equity and benefits accompany the role. Applications accepted until July 26, 2026.

Qualifications

• BS, MS or PhD in CS/EE/CE or related field.
• 15+ years of deep learning and systems design experience.
• Proficiency in Python and C++ programming.
• Strong understanding of computer architecture and GPU computing.

Responsibilities

• Research and develop generative AI, agents, and inference systems into the NVIDIA LLM software stack.
• Analyze workloads and optimize agentic LLM workloads to reduce latency and increase throughput.
• Design scalable systems to accelerate agentic workflows for datacenter-scale use cases.
• Collaborate with diverse teams and external partners to formalize requirements.

Skills

Python

C++

Deep learning systems

Performance modeling

Education

BS/MS/PhD in Computer Science, Electrical Engineering, Computer Engineering, or related field

Tools

CUDA

OpenCL

GPU architecture

Job description

NVIDIA seeks outstanding engineers to advance LLM inference, optimizing agentic workloads and building scalable, datacenter-scale systems. You will contribute to performance-enhancing algorithms and protocols that push the boundaries of what's possible with large language models.

Required: advanced degrees and 15+ years in deep learning, strong Python/C++ skills, and deep knowledge of GPU/parallel computing. Equity and benefits accompany the role. Applications accepted until July 26, 2026.