Deep Learning PhD Research Intern, Reinforcement Learning for LLMs

Nvidia

Confirmed live yesterday High trust

Quick summary

Work type
On-site
Location
Santa Clara, CA
Employment
Intern
Posted
128 days ago
Freshness
Confirmed live yesterday
Nearby
99+ roles within 25 mi

Market check

Salary context

How this pay compares to similar roles

Similar $228k
$172k most similar roles pay here $300k

This listing doesn't post a salary. Most similar roles pay $200,662–$254,750.

Based on 240 similar postings.

Employer

About Nvidia

Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing

Nvidia currently has 896 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 876 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Deep Learning PhD Research Intern, Reinforcement Learning for LLMs

Role Posting Log in to save

Applied Deep Learning PhD Research Intern, Reinforcement Learning for LLMs - Fall 2026 will join the applied deep learning research team to advance the next generation of large language models through reinforcement learning. This role focuses on algorithmic research at the intersection of reinforcement learning and large language models. You will design, implement, and evaluate new RL-based methods to improve model reasoning, alignment, instruction following, and multi-turn interaction while prototyping at scale. Day-to-day tasks involve developing algorithms, designing experiments to evaluate robustness and hallucination, and running experiments on large-scale GPU clusters. The role requires expertise in Python and PyTorch, with a strong background in reinforcement learning and natural language processing. You will work on the technical challenge of improving model behavior and reliability through methods like RLHF, RLAIF, policy optimization, reward modeling, and agentic LLM systems.

Skills

Reinforcement Learning Large Language Models Python PyTorch Deep Learning RLHF RLAIF Natural Language Processing Policy Optimization Reward Modeling GPU Clusters

What you'll do

  • Develop and prototype reinforcement learning algorithms for large language models.
  • Explore methods to improve model reasoning, alignment, and instruction following.
  • Design experiments to evaluate model behavior, robustness, and task performance.
  • Implement research ideas using Python and PyTorch.
  • Run experiments on large-scale GPU clusters.
  • Perform rapid prototyping of RL-based methods for improving LLM behavior.

What we're looking for

  • Pursuing a PhD in AI, ML, CS, CE, EE, Math, Physics, or a related field.
  • Strong background in reinforcement learning and natural language processing.
  • Excellent programming skills, specifically in Python.
  • Experience with deep learning frameworks such as PyTorch.
  • Comfort with experimental research, debugging models, and working with large-scale training pipelines.
  • Publications or open-source contributions in RL, LLMs, alignment, reasoning, or post-training.
  • Experience with RLHF, RLAIF, policy optimization, reward modeling, or agentic LLM systems.
  • Strong intuition for both algorithms and large-scale implementation.

Related searches

More Applied Deep Learning PhD Research Intern jobs Applied Deep Learning PhD Research Intern jobs in Santa Clara All jobs at Nvidia

More like this

Similar roles

Applied Research Intern, NLP

Nvidia

Santa Clara, CA 72 days ago
Python Deep Learning Natural Language Processing PyTorch JAX NeMo-RL Nemotron open-source Model Post-training
Save

PhD Research Intern, Generative AI

Nvidia

Santa Clara, CA 107 days ago
Generative AI Multimodal Foundation Models World Models Python PyTorch Computer Vision Reinforcement Learning Distributed Training Robotics Autonomous Driving Video Understanding Simulation VLMs Policy Learning
Save

Research Scientist, Efficient Deep Learning

Nvidia

Santa Clara, CA 92 days ago $168,000–$264,500
Deep Learning Computer Vision Python PyTorch C++ CUDA Large Language Models Vision-Language Models Pruning Quantization NAS Parallel Programming
Save

Ph.D. Research Computer Vision and Deep Learning Intern

Nvidia

Santa Clara, CA 23 days ago
Computer Vision Deep Learning Python C++ CUDA PyTorch TensorFlow 3D Vision Scene Understanding Neural Rendering Diffusion Models NeRFs Vision Transformers Neural Architecture Search Synthetic Data Generation
Save

Ph.D. Research Large Language Models Intern

Nvidia

Santa Clara, CA 23 days ago
Large Language Models Multimodal Models Python C++ CUDA PyTorch TensorFlow JAX Deep Learning Transformer Architectures Model Compression Quantization Reinforcement Learning Retrieval-Augmented Generation (RAG) Neural Architecture Search Instruction Tuning Knowledge Distillation Data Synthesis
Save