Senior AI Evaluation Architect for Frontier Models

NVIDIA; Schweiz; Vor Ort; CHF 180.000 - 240.000; Vollzeit

Zusammenfassung

NVIDIA is seeking senior engineers to design and implement evaluation environments for frontier AI models, including LLMs and multimodal systems, ensuring reliable, auditable signals drive model releases.

You will build evaluation infrastructure, run large-scale experiments on HPC clusters, and communicate results to researchers, product teams, and leadership to guide release decisions and product strategy.

Qualifikationen

• BS, MS, or PhD in Computer Science, Machine Learning, Statistics, or a related field.
• 6+ years of hands-on experience with LLMs, evaluating large language models or multimodal AI systems.
• Strong statistical foundations: experimental design, significance testing, regression analysis.
• Proven experience building evaluation infrastructure (pipelines, benchmark harnesses, reproducible CI systems).
• Clear, precise communicator who can translate evaluation results to researchers, product teams, and leadership.

Aufgaben

• Design and build evaluation environments for frontier models (reasoning, multimodal, long-context, agentic).
• Research and develop evaluation methodologies for emerging model families and domains.
• Build and operate evaluation pipelines, regression CI, and analysis tooling across teams.
• Partner with model research, training, and customer teams to translate evaluation signals into concrete decisions.

Kenntnisse

LLMs experience

Evaluation design

Statistical analysis

CI pipelines

Communication skills

HPC/Slurm

Python

Ausbildung

BS/MS/PhD in CS/ML/Statistics

Tools

MLflow

Weights & Biases (W&B)

Slurm

Jobbeschreibung

NVIDIA is seeking senior engineers to design and implement evaluation environments for frontier AI models, including LLMs and multimodal systems, ensuring reliable, auditable signals drive model releases.

You will build evaluation infrastructure, run large-scale experiments on HPC clusters, and communicate results to researchers, product teams, and leadership to guide release decisions and product strategy.