{"html":"<p>We&#39;re assembling a group of senior software and ML engineers to work on one of the hardest open problems in AI today: how well can frontier models reason about LLM inference systems, GPU-level performance optimization, and model-serving architecture? You&#39;ll help design evaluation scenarios, write reference solutions, and grade model outputs on real systems-engineering problems — the same class of problems you likely work on day-to-day.</p>\n<p>This is a research-and-evaluation role, not a traditional engineering job — you won&#39;t be shipping production code for us, you&#39;ll be defining what &quot;correct&quot; and &quot;excellent&quot; look like for AI models tackling the problems you already know deeply.</p>\n<h3>Responsibilities</h3><ul><li>What You&#39;ll Do Design realistic technical scenarios and problem sets in LLM inference optimization, GPU kernel design, and systems performance engineering</li></ul><h3>Requirements</h3><ul><li>Bachelor&#39;s degree or higher in Computer Science, Computer Engineering, Electrical Engineering, or a related field</li><li>Strong, hands-on background in one or more of: GPU inference optimization, custom CUDA kernel development, model-serving systems (e.g., vLLM, TensorRT-LLM, SGLang), quantization, or optimizer design</li><li>Experience at a recognized technology or AI company, in a role with real systems-engineering ownership</li><li>Strong written communication — you&#39;ll be authoring technical explanations and feedback, not just code</li></ul><h3>Preferred qualifications</h3><ul><li>Direct experience with SGLang, Mamba/Mamba2 architectures, or IBM Granite-family models</li><li>Open-source contributions to inference/serving frameworks (vLLM, SGLang, TensorRT-LLM, etc.)</li><li>Experience with distributed inference (tensor/expert parallelism, continuous batching, KV-cache optimization)</li></ul>"}