Similar Jobs
See allResearch Engineer Intern
Sony AI
US
Machine Learning
Reinforcement Learning
Prompt Engineering
Research Engineer / Scientist - Reinforcement Learning
Prime Intellect
Global
Python
PyTorch
Reinforcement Learning
Research Engineer, Post-Training
Pluralis Research
Global
Python
PyTorch
Reinforcement Learning
Senior AI Engineer
EnableComp
US
Python
PyTorch
Reinforcement Learning
Research Scientist
EdgeRunner AI
US
Reinforcement Learning
About the role:
- Drive innovation in multi-modal reinforcement learning for next-generation intelligent systems.
- Develop and scale RL techniques in complex architectures, including diffusion models and autoregressive models.
- Build RL infrastructure and reward modeling to enable efficient large-scale training.
Key responsibilities:
- Conduct research on RL algorithms for multimodal models and unified frameworks.
- Design robust benchmarking and evaluation protocols for multimodal tasks.
- Analyze and optimize policy performance across modalities, mitigating reward hacking.
What we're looking for:
- Master's degree in CS or related field; PhD preferred with strong research track record.
- Experience running large-scale RL experiments in multimodal and vision-centric systems.
- Proficiency in PyTorch and deep learning frameworks, with end-to-end RL pipeline experience.
Tether Operations Limited
Tether is a fintech company pioneering digital finance solutions, including the stablecoin USDT, and developing energy, data, and education products. The company is a fast, lean global team of top talent working remotely across the world, with a culture focused on innovation and transparency.