Responsibilities
- Build agent-to-agent protocols where digital workers coordinate, make decisions, and execute financial transactions securely.
- Design and develop specialized agents tailored to handle specific tasks, such as supporting risk management, ensuring compliance, or even creating other AI agents.
- Use expertise in AI agent development, including evaluation methods, system design, and prompt engineering, ensuring each agent is equipped with the right tools and clear instructions on when and how to use them.
- Build the foundational elements for how agents will pay and get paid in an autonomous future, with human-in-the-loop when appropriate.
- Develop identity and memory architecture that helps agents build reputation, learn from the past and reason in context.
- Create cross-language SDKs and dev tools for developers building in agent ecosystems like MCP, A2A, LangChain, CrewAI, Vercel AI, Pydantic and beyond, across multiple languages like TypeScript and Python.
- Build systems for testing, tuning, and continuously improving agent behaviors and decision-making.
Requirements
- Experience leveraging AI tools effectively to multiply productivity, streamline processes, and enhance decision-making.
- Experience shipping scalable agent-based or LLM-integrated systems in production environments.
- Familiarity with, and frequent use of, modern AI tools and frameworks, such as MCP and A2A, with a finger on the pulse of the industry.
- Clear understanding of how to structure agents with short and long-term memory, as well as when and how to create a separation of concerns.
- Deep interest in how and why identity and economic agency intersect in AI systems.
- A track record of navigating ambiguity, proposing architecture, and building systems that scale.
- Curiosity about what makes AI agents safe, useful, and autonomous, and the drive to improve that every day.
- Comfort with fast-paced environments where 0→1 thinking is not a phase — it’s the job.
