AI Educator — Agents, Automation & Vibe Shipping

About the role

We're looking for a builder who can make technical AI digestible through working projects and clear explanations.

You'll design and teach AI agents, automations, and applications that solve concrete problems. Projects might include a research assistant that cites its sources, a document assistant that retrieves relevant information, or an automation that connects business tools with human review at key steps.

You'll own the journey from a working prototype to a lesson learners can reproduce: testing the system, explaining architecture and tradeoffs, recording the build, and providing useful code or workflow templates.

What you'll do

Build and teach projects using LLMs, tool calling, structured outputs, retrieval-augmented generation (RAG), and agent workflows.
Connect AI systems to external tools and data through APIs, webhooks, and the Model Context Protocol (MCP), where appropriate.
Explain when to use a simple automation, a defined workflow, or an agent.
Produce clear technical walkthroughs, live coding sessions, written guides, and reusable project resources.
Teach debugging and evaluation alongside implementation, including handling failures, measuring output quality, and managing latency and cost.
Cover deployment concerns such as credentials, data access, logging, and human approval for consequential actions.
Lead workshops and office hours, help learners troubleshoot, and improve materials based on the problems they encounter.
Maintain examples as dependencies and model behavior change, with clear setup instructions and tested outputs.

What we're looking for

Evidence that you've built working AI applications, agents, or automations beyond basic chat prompts.
Confidence in Python or JavaScript/TypeScript, including APIs, JSON, authentication, and Git.
Practical understanding of tool calling, retrieval, context management, and the limitations of language models.
Experience with an agent framework or automation platform, and the ability to explain the underlying concepts independently of the tool.
The ability to debug your projects and distinguish a convincing demo from a reliable workflow.
Clear written and spoken communication, with confidence teaching through screen recordings and live demonstrations.
The judgment to explain tradeoffs without overwhelming learners, and to acknowledge when an approach fails.

Useful extras

Experience with low-code automation tools alongside code-based development.
Public tutorials, open-source contributions, technical writing, or developer education experience.
Experience deploying AI applications and evaluating their behavior with realistic test cases.
Experience teaching learners with different levels of technical confidence.

What success looks like

Learners can run your projects,
Understand the design choices, and adapt them to their own needs.

Name *

Email *

Share 2 agents, automations, or AI applications you've built. Include repository, demo, or walkthrough links, your contribution, and the problem each solves. *

Share a link to a teaching sample explaining a technical concept or walking through a build. Existing tutorials, articles, and screen recordings are welcome. *

Describe a failure you encountered in an AI project. How did you diagnose it, what did you change, and how did you check that the fix worked? *

Phone *

Expected Compensation *

Record a short video of yourself teaching a concept of your choice relevant to the role in 1 Mins. *

Made withBinary

About the role

We're looking for a builder who can make technical AI digestible through working projects and clear explanations.

What you'll do

Build and teach projects using LLMs, tool calling, structured outputs, retrieval-augmented generation (RAG), and agent workflows.

Connect AI systems to external tools and data through APIs, webhooks, and the Model Context Protocol (MCP), where appropriate.

Explain when to use a simple automation, a defined workflow, or an agent.

Produce clear technical walkthroughs, live coding sessions, written guides, and reusable project resources.

Teach debugging and evaluation alongside implementation, including handling failures, measuring output quality, and managing latency and cost.

Cover deployment concerns such as credentials, data access, logging, and human approval for consequential actions.

Lead workshops and office hours, help learners troubleshoot, and improve materials based on the problems they encounter.

Maintain examples as dependencies and model behavior change, with clear setup instructions and tested outputs.

What we're looking for

Evidence that you've built working AI applications, agents, or automations beyond basic chat prompts.

Confidence in Python or JavaScript/TypeScript, including APIs, JSON, authentication, and Git.

Practical understanding of tool calling, retrieval, context management, and the limitations of language models.

Experience with an agent framework or automation platform, and the ability to explain the underlying concepts independently of the tool.

The ability to debug your projects and distinguish a convincing demo from a reliable workflow.

Clear written and spoken communication, with confidence teaching through screen recordings and live demonstrations.

The judgment to explain tradeoffs without overwhelming learners, and to acknowledge when an approach fails.

Useful extras

Experience with low-code automation tools alongside code-based development.

Public tutorials, open-source contributions, technical writing, or developer education experience.

Experience deploying AI applications and evaluating their behavior with realistic test cases.

Experience teaching learners with different levels of technical confidence.