ML Research Engineer: End-to-End AI Evaluation & Experiments

24-Mag Llc; New York (NY); Remote; USD 100,000 - 155,000; Full time

Job summary

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.

Qualifications

• Master's degree or PhD in machine learning, computer science, AI, engineering, mathematics, or related STEM field.
• Equivalent practical experience in a research-intensive ML role may be considered.
• Publications, open-source contributions, technical reports, or substantial research projects are valuable.

Responsibilities

• Design multi-step evaluation tasks from practical ML research ideas.
• Implement reference solutions using Python, scripts, and notebooks.
• Configure and run training experiments from setup to evaluation.
• Validate code, dependencies, datasets, outputs, and results.
• Document workflows to enable reproducibility.

Skills

Python

Git

Experiment design

Reproducible research

Notebook environments

Analytical reasoning

Communication

Education

Master's degree or PhD in ML/CS/AI

Equivalent practical experience in ML research

Publications/open-source contributions

Tools

Python

Jupyter

Job description

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.