Senior Research Engineer, Generative AI Inference

NVIDIA; United States; Remote; USD 192,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA seeks a Senior Research Engineer focused on Generative AI inference. You will design routing policies for LLM traffic across model systems and build agentic benchmarks to evaluate algorithm quality, feeding results into routing profiles.

You will collaborate across NVIDIA to ensure seamless integration in the serving stack and contribute to open-source docs, reviews, and community work. The role emphasizes deep learning expertise, pragmatic empirical research, and leadership mentoring

Qualifications

• Bachelor’s or Master’s degree in Computer Science or equivalent experience.
• 8+ years of industry experience in Deep Learning frameworks (PyTorch or TensorFlow).
• Experience designing or running LLM evaluations/benchmarks and drawing statistically sound conclusions.

Responsibilities

• Design and evaluate routing policies for LLM traffic to best use mixture of model systems.
• Build and run agentic benchmarks to measure algorithm quality and calibration data.
• Collaborate with engineering teams to ensure seamless integration across NVIDIA's serving stack.
• Ship to an open-source repo: design docs, code reviews, docs, and community contributions.

Skills

Strong communication

Mentoring junior engineers

Analytical mindset

Education

Bachelor’s or Master’s in Computer Science

Tools

PyTorch

TensorFlow

CUDA

Job description

NVIDIA seeks a Senior Research Engineer focused on Generative AI inference. You will design routing policies for LLM traffic across model systems and build agentic benchmarks to evaluate algorithm quality, feeding results into routing profiles.

You will collaborate across NVIDIA to ensure seamless integration in the serving stack and contribute to open-source docs, reviews, and community work. The role emphasizes deep learning expertise, pragmatic empirical research, and leadership mentoring