Research Intern (AI4EDA)

Location: On-site in Palo Alto, California, United States

Company

hirify.global is an AI research and product lab developing models and systems for exploring, designing, optimizing, and verifying hardware.

What you will do

• Co-design and implement reinforcement learning experiments using GRPO, PPO, and DPO.
• Explore training data mixes and reward signals for hardware-design models.
• Research post-training techniques and run ablation studies to improve reasoning and alignment.
• Implement and test model fine-tuning and evaluation algorithms.
• Analyze experimental results and debug model behavior to improve training recipes.

Requirements

• Currently pursuing a PhD or Master's degree in Computer Science, Machine Learning, Mathematics, or a related field; exceptional undergraduates with strong research experience may also apply.
• Strong academic knowledge or project experience in reinforcement learning, including PPO, DPO, or GRPO.
• Strong proficiency in Python and PyTorch, with the ability to write clean, efficient research code.
• Experience training or fine-tuning large language models or familiarity with Transformers and HuggingFace.
• Ability to analyze complex problems, navigate ambiguity, and iterate quickly on experiments.

Nice to have

• Previous internship experience at frontier AI labs or research organizations.
• Publications or submissions to NeurIPS, ICLR, ICML, DAC, or ICCAD.
• Familiarity with hardware design concepts such as Verilog, RTL, or EDA tools.

Culture & Benefits

• Three-month internship working alongside the founding team.
• Competitive internship stipend.
• Mentorship from researchers and engineers with experience at Anthropic, DeepMind, Meta, and Stanford.
• Opportunity to work on early-stage AI-driven chip-design problems.