Descripción del puesto
<p style="min-height:1.5em">Our mission is to automate coding. The first step in our journey is to build the best tool for professional programmers, using a combination of inventive research, design, and engineering. Our organization is very flat, and our team is small and talent dense. We particularly like people who are truth-seeking, passionate, and creative. We enjoy spirited debate, crazy ideas, and shipping code.</p><h2>Research Scientist</h2><p style="min-height:1.5em">Cursor is building the future of coding. We train <a target="_blank" rel="noopener noreferrer nofollow" href="https://cursor.com/blog/composer">frontier coding agents</a> and scale RL on real user data to make them increasingly effective.</p><p style="min-height:1.5em"></p><h2>About the role</h2><p style="min-height:1.5em">We’re looking for Research Scientists who can drive effective RL or mid-training research in a small-team setting. You’ll own ambiguous, hard research problems end-to-end: forming hypotheses, designing experiments, building the training/eval/data needed to test them, and pushing results into the next model. You should expect significantly more scope and autonomy than in other research labs.</p><p style="min-height:1.5em"></p><h2><strong>What you’ll do</strong></h2><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Improve our understanding of RL, what it takes to handle longer horizon tasks, and train with less compute</p></li><li><p style="min-height:1.5em">Train graders to improve performance on coding tasks with non-verifiable reward</p></li><li><p style="min-height:1.5em">Improve the quality and difficulty of datapoints we use for training our models</p></li><li><p style="min-height:1.5em"><a target="_blank" rel="noopener noreferrer nofollow" href="https://cursor.com/blog/tab-rl">Realtime RL</a> for coding agents</p><p style="min-height:1.5em"></p></li></ul><h2>You may be a fit if</h2><ul style="min-height:1.5em"><li><p style="min-height:1.5em">You have a deep background in RL and strong machine learning fundamentals</p></li><li><p style="min-height:1.5em">You’re an excellent programmer and software engineer</p></li><li><p style="min-height:1.5em">You can handle ambiguous research tasks with little guidance</p></li><li><p style="min-height:1.5em">You care a lot about data quality, and can dive into the data when appropriate</p></li><li><p style="min-height:1.5em">You are truth seeking, aiming to learn more about the science than proving your ideas are correct.</p></li></ul><p style="min-height:1.5em">#LI-DNI</p>