Remote AI Research Engineer: Agentic RL

Jobgether; España; Remote; EUR 90,000 - 140,000; Full time

Benefits offered by this job

Fully remote work

International collaboration

Cutting-edge AI research

Publish opportunities

Job summary

Jobgether is seeking an AI Research Engineer specializing in Agentic Reinforcement Learning, based in Spain. You will advance research in multimodal AI, designing scalable RL pipelines and reward models across text, image, audio, and other modalities.

You will experiment with diffusion-based and autoregressive systems, and publish results at top conferences. The role is fully remote within a global team, offering opportunities to shape cutting-edge AI technologies and contribute to high-impact

Qualifications

• Master's degree in Computer Science or related field; PhD preferred.
• Strong track record of AI research with publications at top conferences.
• Experience conducting large-scale RL experiments in multimodal/vision-centric systems.
• Proven ability to improve policy performance in complex environments.
• Deep understanding of RL algorithms and optimization for vision/multimodal learning.
• Knowledge of policy stability, exploration strategies, and sample efficiency in high-dimensional data.

Responsibilities

• Research and develop RL algorithms for multimodal models, including diffusion- and autoregressive-based approaches.
• Design scalable reinforcement learning infrastructure for distributed training.
• Develop reward modeling strategies to improve training stability.
• Create and maintain multimodal simulation environments and datasets.
• Design rigorous evaluation protocols to measure improvements against baselines.
• Publish and present findings at leading conferences.

Skills

Reinforcement learning

Multimodal learning

PyTorch

Research publications

Large-scale experiments

Online RL environments

Policy optimization

Experimentation

Cross-disciplinary communication

Education

Master's degree in Computer Science

PhD in ML/NLP/CS/related field (preferred)

Tools

PyTorch

Job description

Jobgether is seeking an AI Research Engineer specializing in Agentic Reinforcement Learning, based in Spain. You will advance research in multimodal AI, designing scalable RL pipelines and reward models across text, image, audio, and other modalities.

You will experiment with diffusion-based and autoregressive systems, and publish results at top conferences. The role is fully remote within a global team, offering opportunities to shape cutting-edge AI technologies and contribute to high-impact