Senior Research Engineer — RL Systems & Evaluation (Remote)

24-Mag Llc; New York (NY); Remote; USD 400,000 - 800,000; Full time

Benefits offered by this job

Fully remote

Job summary

24-MAG LLC is seeking a highly experienced Research Engineer for a fully remote role focused on reinforcement learning, ML data systems, evaluation infrastructure, and scalable experimentation to advance AI research and development.

You will build RL environments, training pipelines, synthetic data systems, and automated evaluation frameworks, translating research ideas into robust systems that improve model capability, reliability, and research velocity across large-scale experiments.

Qualifications

• Deep RL expertise and ability to design and scale RL environments.
• Experience building scalable ML systems and experimentation workflows.
• Strong automation and evaluation capabilities.

Responsibilities

• Architect self-contained reinforcement-learning environments for complex tasks.
• Design reward functions, verifiers, and evaluation logic.
• Scale episode pipelines and multi-component training processes.
• Build reproducible experimentation workflows for RL research.
• Develop systems for running, tracking, and analysing large-scale training experiments.
• Improve reliability and efficiency across RL training infrastructure.

Skills

Reinforcement Learning

Experimentation Frameworks

Automation

Evaluation Systems

Job description

24-MAG LLC is seeking a highly experienced Research Engineer for a fully remote role focused on reinforcement learning, ML data systems, evaluation infrastructure, and scalable experimentation to advance AI research and development.

You will build RL environments, training pipelines, synthetic data systems, and automated evaluation frameworks, translating research ideas into robust systems that improve model capability, reliability, and research velocity across large-scale experiments.