Senior Deep Learning Engineer

Overview

In this role you will design and implement evaluation environments for frontier AI models, including LLMs and multimodal systems, to produce auditable accuracy signals guiding model releases. You’ll research novel evaluation methods for emerging model families and scale evaluation pipelines used by model, product, and research teams. You’ll collaborate across disciplines to translate signals into concrete release and iteration decisions, while working on enterprise-grade GPU clusters and cutting-edge hardware.

This is your chance to influence NVIDIA’s roadmap and shape the AI landscape.

• Design decision-grade evaluation environments for frontier models (reasoning, multimodal, long-context, agentic systems)
• Research and develop novel evaluation methodologies for emerging model families
• Build and operate evaluation infrastructure and pipelines (benchmark environments, regression CI, statistical tooling)
• Partner with model research, training, and customer teams to translate signals into release decisions and competitive positioning against external frontier models

• 6+ years of hands-on experience with LLMs and 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)
• Clear, precise communication; ability to translate quantitative results into decisions for researchers and leadership
• Collaborative cross-functional mindset
• Strong problem-solving and analytical thinking
• Experience with LLM evaluations, agentic/multi-turn/reasoning-heavy settings
• Open-source evaluation frameworks knowledge (standout)
• Experience measuring model accuracy under low-precision inference (FP8, INT4)

Salary: EUR 63000 - 77000 per year