RL Research Engineer: Scalable Training & Eval (Remote)

24-MAG; United States; Remote; USD 400,000 - 800,000; Full time

Job summary

24-MAG LLC is seeking a remote Member of Technical Staff in Research Engineering with deep RL expertise. The role spans RL environment design, scalable training pipelines, synthetic data generation, automated evaluation, and benchmarking to accelerate AI research and development.

You will work at the interface of research and production, building RL environments, training workflows, and evaluation systems that improve model capability, reliability, and research velocity in a fully remote,

Qualifications

• Deep professional or research experience in reinforcement learning.
• Strong understanding of RL environment design, reward structures, training dynamics, and evaluation.
• Demonstrated experience building and scaling RL systems, training pipelines, or experimentation frameworks.
• Strong experience with automation and synthetic data-generation workflows.
• Familiarity with automated evaluation, model validation, and quality-assurance systems.
• Experience fine-tuning and evaluating open-source machine-learning models.
• Strong technical writing and communication skills.
• Ability to operate effectively in fast-paced, research-driven environments.

Responsibilities

• Reinforcement Learning Environment Design: architect self-contained RL environments and design rewards, verifiers, and evaluation logic.
• Training Pipelines & Experimentation Systems: design scalable episode pipelines and reproducible experimentation workflows.
• Synthetic Data & Automated Evaluation: build automated data-generation systems and automated evaluation and QA systems.
• Model Optimisation & Benchmarking: fine-tune open-source RL/ML models and develop benchmarking frameworks.
• Cross-functional collaboration to translate research goals into robust, production-ready systems.

Skills

Reinforcement Learning

RL Environments

Training Pipelines

Experimentation Systems

Synthetic Data Generation

Automated Evaluation

Model Benchmarking

Open-source ML Models

Automation & Pipelines

Technical Writing

Job description

24-MAG LLC is seeking a remote Member of Technical Staff in Research Engineering with deep RL expertise. The role spans RL environment design, scalable training pipelines, synthetic data generation, automated evaluation, and benchmarking to accelerate AI research and development.

You will work at the interface of research and production, building RL environments, training workflows, and evaluation systems that improve model capability, reliability, and research velocity in a fully remote,