Senior Agentic RL Research Engineer Remote

Jobgether; Australia; Remote; AUD 120,000 - 180,000; Full time

Benefits offered by this job

Fully remote work from anywhere

Globally distributed team

Opportunities to publish at major AI/0

Job summary

Jobgether seeks an AI Research Engineer (Agentic Reinforcement Learning) based in Australia. The role focuses on advancing reinforcement learning for multimodal AI systems, including diffusion-based and autoregressive models, with scalable training infrastructure and rigorous evaluation.

The ideal candidate has a strong publication record and hands-on experience building end-to-end RL pipelines. This fully remote opportunity involves working in a globally distributed team and contributing to

Qualifications

• Master's degree in CS or related field; PhD preferred.
• Strong AI research track record with publications at top conferences.
• Experience in large-scale RL experiments in multimodal/vision systems.
• Proficiency in PyTorch and modern deep learning frameworks.

Responsibilities

• Conduct advanced research and develop scalable reinforcement learning systems for multimodal AI applications.
• Design scalable reinforcement learning infrastructure for distributed training across complex multimodal systems.
• Develop and optimize reward modeling strategies to improve training stability and alignment with goals.
• Create, curate, and maintain multimodal simulation environments and training datasets.

Skills

Reinforcement learning

Multimodal learning

Academic publications

Experiment design

Research communication

Education

Master's degree in Computer Science or related field

PhD in ML / NLP / CV preferred

Tools

PyTorch

Deep learning frameworks

Job description

Jobgether seeks an AI Research Engineer (Agentic Reinforcement Learning) based in Australia. The role focuses on advancing reinforcement learning for multimodal AI systems, including diffusion-based and autoregressive models, with scalable training infrastructure and rigorous evaluation.

The ideal candidate has a strong publication record and hands-on experience building end-to-end RL pipelines. This fully remote opportunity involves working in a globally distributed team and contributing to