24-MAG LLC is offering a fully remote, full-time opportunity for machine learning engineers and research practitioners to design, implement, and evaluate end-to-end ML benchmarks.
You will transform real ML ideas into multi-step tasks, run experiments in Python notebooks, analyze training behavior, and assess model-generated solutions for correctness. Collaboration with researchers and task authors is expected, with ~35 hours/week and competitive hourly rates.
#J-18808-Ljbffr