Remote AI Research Engineer - Agentic Multimodal RL

Jobgether; Italia; Remote; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Fully Remote

International collaboration

Cutting-edge research

Publish opportunities

Professional growth

Global team

Job summary

Jobgether is seeking an AI Research Engineer (Agentic Reinforcement Learning) based in Italy for a fully remote role. You will advance multimodal reinforcement learning, design scalable training infra, and develop reward mechanisms to improve agent behavior across text, images, and audio modalities.

You will publish findings at major conferences and contribute to practical AI solutions within a fast-moving, globally distributed environment.

Qualifications

• Master's degree or PhD in a related field with strong AI focus.
• Proven track record in AI research with publications at major conferences.
• Experience conducting large-scale reinforcement learning experiments in multimodal/vision-centric systems.
• Ability to translate research into practical AI solutions.

Responsibilities

• Research and develop RL algorithms for multimodal models including diffusion and autoregressive approaches.
• Design scalable RL infrastructure for distributed training across multimodal systems.
• Develop reward modeling to improve training stability and policy performance.
• Create and curate multimodal simulation environments and datasets for benchmarking.
• Establish rigorous evaluation protocols to measure progress against baselines.
• Analyze policy performance across modalities and optimize cross-modal alignment.
• Explore emerging RL paradigms to improve agent learning from feedback.
• Improve exploration, decision-making, and adaptability in dynamic environments.
• Conduct large-scale experiments and translate findings into algorithms.
• Publish and present research at ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV.

Skills

Reinforcement learning

Multimodal learning

Research publications

Experimentation

Python

Policy optimization

Online RL

AI research

Education

Master's degree in Computer Science or related field

PhD in ML/NLP/CV or related field preferred

Tools

PyTorch

Job description

Jobgether is seeking an AI Research Engineer (Agentic Reinforcement Learning) based in Italy for a fully remote role. You will advance multimodal reinforcement learning, design scalable training infra, and develop reward mechanisms to improve agent behavior across text, images, and audio modalities.

You will publish findings at major conferences and contribute to practical AI solutions within a fast-moving, globally distributed environment.