Research Scientist Graduate (Seed Model-Alignment&Preparedness) - 2027 Start

What you'll do

• Train agents for safe and controllable behavior using RL, SFT, and preference optimization; design environments, rewards, and data to reduce unsafe actions.
• Assess frontier risks and build safeguards, automated red teaming, monitoring, and oversight methods.
• Analyze failures, run controlled experiments, and collaborate with research, engineering, infrastructure, and product teams to deploy effective methods.

What they ask for

• Completing or recently completed a BS in Computer Science, Electrical Engineering, Electrical and Computer Engineering, Physics, Mathematics, or a related discipline.
• Strong foundations in ML, deep learning, and statistics, plus research or engineering experience in LLMs, RL, or related fields.
• Proficiency in Python and PyTorch (or similar), including implementing algorithms, building experiment pipelines, and debugging.
• Deep hands-on experience in at least one of agent RL, model training, dataset development, agent systems, evaluation, or ML infrastructure.

Nice to have

• Completing or recently completed an MS in a listed or related discipline.
• Experience with SFT, RLHF/RLAIF/RLVR, distributed training, automated red teaming, or related safety research and risk evaluation.

Tools

Python, PyTorch, RL, SFT, RLHF/RLAIF/RLVR

AI focus

AI safety research involving agent RL, alignment, frontier risk assessment, automated red teaming, monitoring, and oversight.