We are seeking research interns to pioneer new methodologies for accurately assessing and understanding the performance of ground-breaking deep learning models, including LLMs, RAG, agents, and multimodal models. You will collaborate with our research and development team to define and execute on new research directions that improve our understanding of LLM capabilities through actionable analysis on model accuracy and token efficiency. The relevant research topics include but are not limited to: model and agent evaluation, failure analysis, interpretability, reasoning efficiency, benchmark creation for real-world tasks, safety and robustness. During the internship, you will have the opportunity to collaborate with an excellent team that conducts research and creates production-ready evaluation tools like Nemo Evaluator .

This role offers an outstanding opportunity to craft the future of AI at a fast-growing company at the forefront of the AI revolution. Join our team of world-class software engineers and researchers to deliver the most advanced models with lightning-fast inference. You'll work on the most powerful, enterprise-grade GPU clusters capable of hundreds of PetaFLOPS and gain early access to unreleased hardware, making a direct impact on NVIDIA's roadmap and the broader AI landscape!

What you’ll be doing:

• Research and develop innovative deep learning methodologies to evaluate and understand new model families across diverse capabilities.

• Research, prototype, and build robust tools and infrastructure pipelines to support and inform our ground-breaking AI initiatives in building and evaluating models and agentic systems.

• Contribute to NVIDIA's open-source contributions including: AI/DL libraries and LLM ecosystem.

What we need to see:

• You are currently enrolled in a PhD program in Computer Science, AI, Applied Math, or a related field.

• A publication record in venues like NeurIPS, ICML, ICLR, AAAI, FAccT, ACL.

• Strong problem-solving, debugging, performance analysis, test design, and documentation skills.

• Solid mathematical foundations and expertise in AI/DL algorithms.

• Hands-on experience with Deep Learning frameworks (e.g. PyTorch, TensorFlow).

• Excellent written and verbal communication skills, with the ability to work both independently and collaboratively in a fast-paced environment.

Ways to stand out from the crowd:

• Experience on research topics relevant to one or more of the following directions: model and agent evaluation, failure analysis, interpretability, reasoning efficiency, benchmark creation, safety and robustness.

• Experience in accuracy and token efficiency evaluation of LLMs and agentic systems.

• Hands-on experience with inference and deployment environments like TensorRT, vLLM, SGLang, ONNX, or Triton.

• Experience with running workloads in high-performance computing (HPC) and cloud clusters.

NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

Applications will be accepted until: December 26, 2025.

Please note: We will be reviewing applications on a rolling basis as they are submitted. We encourage you to apply early.