Machine Learning Expert, AI Agent Evaluation

What you'll do: You'll take problems from your own work and turn each one into a self-contained task that an AI agent has to solve in a Linux terminal. For every task, you'll do four things: Write a clear brief. Set up the environment with the files and tools the agent needs. Build a reference solution. Write automated checks on the final result. The strongest tasks are the ones today's best agents still get wrong. Your firsthand knowledge of where real machine learning work goes wrong is what makes them valuable. That might be a data loader that leaks the test split, a learning-rate schedule that diverges after warmup, an inference server that degrades under batching, or a GPU kernel with an off-by-one in its tiling. Specialties we're looking for If your background is in machine learning, there's likely a place for you. We're building depth across: Training: pretraining, fine-tuning, distributed training, and optimization Inference: serving, quantization, batching, and latency Evaluation: benchmarks, metrics, and evaluation harnesses Kernels: CUDA, Triton, and performance engineering Who we're looking for Academics and practitioners are equally welcome. We're after your machine learning expertise and your comfort working in a terminal.