Member of Technical Staff - Research Intern

What you'll do

• Design and implement reinforcement learning experiments, training data mixes, and reward signals.
• Research post-training techniques and run ablation studies to improve model reasoning and alignment.
• Implement and evaluate fine-tuning algorithms, analyze results, and debug model behavior.

What they ask for

• Currently pursuing a PhD or Master’s in Computer Science, Machine Learning, Mathematics, or a related field; exceptional undergraduates with strong research experience are also encouraged to apply.
• Strong academic understanding or project experience with reinforcement learning, such as PPO, DPO, or GRPO.
• Strong proficiency in Python and PyTorch.
• Experience training or fine-tuning LLMs, or familiarity with the modern NLP stack.

Nice to have

• Previous internship at a frontier AI lab or research organization; publications or submissions to top ML or EDA venues.
• Familiarity with hardware design concepts, including Verilog, RTL, or EDA tools.

Tools

Python, PyTorch, PPO, DPO, GRPO, Transformers, HuggingFace, Verilog

AI focus

Research and implement reinforcement learning, post-training, fine-tuning, and evaluation methods for models that explore and optimize hardware designs.