Research Engineer / Scientist, Self-Improvement

What you'll do

• Develop prompt optimization and system prompt learning for continuous learning on long-horizon tasks.
• Create methods for agents to generate and test hypotheses or identify and improve their weaknesses; make learning from long-running tasks more efficient.
• Design and run scalable experiments to measure self-improvement.

What they ask for

• Expertise in machine learning, particularly LLMs and continual learning.
• Familiarity with agent frameworks and prompt optimization.
• Track record of impactful research through breakthrough publications and/or open-source contributions.
• Ability to balance execution speed with empirical rigor and demonstrate real-world impact beyond academic work.

Tools

LLMs

AI focus

Research and engineering for agents that self-improve after training, including prompt and system-prompt learning, hypothesis testing, and learning from long-running tasks.