Software/ML Engineer

About the Role

We are assembling a group of senior software and machine learning engineers to tackle one of AI's most challenging open problems: evaluating how well frontier models reason about LLM inference systems, GPU-level performance optimization, and model-serving architecture. You will design realistic technical scenarios, write reference solutions, and grade model outputs on real systems-engineering challenges.

Role Nature

This is a research-and-evaluation role focused on defining what 'correct' and 'excellent' look like for AI models, rather than traditional production code shipping. This position offers flexible remote work as a contract or part-time arrangement with no fixed schedule requirements.

Responsibilities: What You'll Do

• Design realistic technical scenarios and problem sets in LLM inference optimization.
• Develop expertise in GPU kernel design and systems performance engineering.

Required Qualifications

• Bachelor's degree or higher in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• Strong hands-on background in one or more of the following: GPU inference optimization, custom CUDA kernel development, model-serving systems (e.g., vLLM, TensorRT-LLM, SGLang), quantization, or optimizer design.
• Experience at a recognized technology or AI company with real ownership over systems-engineering projects.
• Strong written communication skills for authoring technical explanations and feedback.

Preferred Qualifications

• Direct experience with SGLang, Mamba/Mamba2 architectures, or IBM Granite-family models.
• Open-source contributions to inference/serving frameworks (vLLM, SGLang, TensorRT-LLM).
• Experience with distributed inference techniques including tensor/expert parallelism, continuous batching, and KV-cache optimization.