Sr. Model Engineer, RL Training Framework

<div class="content-intro"><p>SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the technologies to make this possible, with the ultimate goal of making life multiplanetary and expanding consciousness to the stars.<br><br>SpaceXSI is building Super Intelligence to help humanity understand the universe. Our teams are building the full Super Intelligence stack: from our Colossus supercomputers, to Grok models, to our suite of applications, including Grok Bot, Grok Build, Grok Imagine, Grok Voice, and X. We're creating a powerful flywheel where more compute trains better models, better models power more useful products, and what we learn from people using those products shapes what we build next.</p></div><h4><strong>SR. MODEL ENGINEER, RL TRAINING FRAMEWORK</strong></h4> <p>The RL infrastructure team is looking for an engineer to help develop our RL training framework.</p> <h4><strong>RESPONSIBILITIES:</strong></h4> <ul> <li>Design and implement the systems backing all RL workloads at SpaceXSI, from small scale ablations to production training runs</li> <li>Profile, debug, and optimize end-to-end training performance</li> <li>Improve scalability and observability of the RL stack</li> </ul> <h4><strong>BASIC QUALIFICATIONS:</strong></h4> <ul> <li>Experience writing production-quality code in Python, PyTorch, JAX, Rust, or C++</li> <li>Experience training large models (e.g., pre-training, post-training, fine-tuning, or RL training of neural networks with 1B+ parameters)</li> </ul> <h4><strong>PREFERRED SKILLS AND EXPERIENCE:</strong></h4> <ul> <li>Experience building, debugging, and optimizing efficiency of large-scale distributed systems</li> <li>Experience with large scale LLM training infrastructure</li> <li>Experience with RL numerics</li> <li>Strong knowledge of reinforcement learning techniques</li> <li>Comfortable diving into un