To apply, send us your resume and anything else you'd like to [email protected]

About Amigo

We're helping enterprises build autonomous agents that reliably deliver specialized, complex services—healthcare, legal, and education—with practical precision and human-like judgment. Our mission is to build safe, reliable AI agents that organizations can genuinely depend on. We believe superhuman level agents will become an integral part of our economy over the next decade, and we've developed our own agent architecture to solve the fundamental trust problem in AI. Learn more here.

Role

As a Researcher in Agent Development at Amigo, you'll investigate and enhance the unified Memory-Knowledge-Reasoning (M-K-R) cycle that forms the foundation of our agent architecture. Working as part of our Research team, you'll research methods to increase the bandwidth between these integrated cognitive systems and develop techniques that enable agents to handle complex, long-horizon problems with less external scaffolding. Your work will focus on improving context engines, memory systems, knowledge activation, and reasoning pathways as an integrated whole, driving our Agent V2 architecture toward greater autonomy and reliability. This research is critical for overcoming the token bottleneck limitation and preparing for future neuralese capabilities.

Responsibilities

• Research methods to enhance the integration bandwidth between memory, knowledge, and reasoning systems to enable more complex agent capabilities
• Develop techniques for dynamic abstraction control that allow agents to seamlessly move between different granularity levels depending on reasoning needs
• Design approaches for contextual reframing that transform stored information into optimal configurations for specific tasks
• Create frameworks for quantized problem decomposition that break complex challenges into tractable units while maintaining progress toward larger goals
• Research methods for optimizing the inner ↔ outer world information flow, including intelligent contextual compression and processing
• Develop techniques that reframe reasoning steps as bounded optimization problems with explicit constraints and context
• Design and implement checkpointing mechanisms that enable long-horizon reasoning while maintaining coherent progress
• Investigate approaches for optimizing latent-space priming and knowledge activation to directly shape problem-space transformation
• Collaborate with the Memory team to enhance the memory-reasoning bridge across our layered architecture
• Work with the Reinforcement Learning team to improve agent adaptation under evolutionary pressure