Junior Research Scientist at dmodel (S24) $100K - $200K • 0.10% - 0.50% Look inside the model San Francisco, CA, US Full-time Will sponsor Any (new grads ok) About dmodel About the role d_model is seeking a Junior Research Scientist to join us in automating alignment and understanding how models conduct AI research. We partner with frontier labs to tackle automated alignment. Your research will make it into their production sota models. Key Responsibilities Run experiments and identify patterns in model behavior and failure modes Find novel interpretability and alignment techniques. Build reinforcement learning environments and evals to test how AI agents approach alignment problems Develop graders robust to specification gaming Present findings in team research meetings and contribute to papers on AI Safety Requirements Bachelor's degree in Computer Science, Mathematics, Physics, or related field, or equivalent experience Strong proficiency in Python and ML frameworks (PyTorch preferred) Ability to generate research ideas in the field and implement others’ ideas. Familiarity with the alignment or interpretability literature. Ability to work full-time in San Francisco, CA Strong candidates may also have: PhD in a related field or equivalent research experience Published or presented research in AI safety Experience with mechanistic interpretability Experience post-training language models Why Join See your research deployed in production models at scale Define an emerging field through published research Work on alignment problems nobody else is solving