AI Instructor – AI APIs

YPAI; United States; Remote; USD 36,000 - 136,000; Full time

Job summary

YPAI Learn is seeking experienced instructors to teach live online classes for developers on calling model APIs from code. The program covers structured output, tool calls, streaming, and managing cost, latency, rate limits, and errors, all taught in English from a ready-made class kit.

You will deliver 90-minute sessions, demonstrate JSON schema validation, streaming tokens, retries with backoff, and how to monitor usage in learners’ logs.

Qualifications

• Hands-on use of model APIs in production code: structured output, tool calling, streaming, retries and usage tracking.
• Experience teaching developers, writing technical tutorials, mentoring or running hands-on coding sessions.

Responsibilities

• Teach the live class “Get validated JSON from a model API with structured output and tool calls”, 90 minutes, from the class kit.
• Teach the live class “Stream, retry and track the cost of model API calls in a backend service”, 90 minutes, from the class kit.
• Show live how a JSON schema and a tool definition shape the response, how to validate it in code, and what to do when the output is cut off at the token limit.
• Walk learners through streaming tokens to a client, measuring time to first token, logging token counts per request and estimating what each feature costs to run.
• Help learners hit by 429 responses, timeouts or server errors, by adding retries with backoff and jitter, honoring retry‑after headers and keeping keys out of client code.

Skills

Backend software

Python

TypeScript

HTTP

JSON

Tools

Python

TypeScript

HTTP

JSON

Asynchronous requests

Job description

Teach live online classes for developers on calling model APIs from code: structured output, tool calling, streaming, and keeping cost, latency, rate limits and errors under control. You teach in English from a ready‑made class kit, remotely, and you are paid for each class you teach.

What the work is for

YPAI Learn runs live coding classes on putting model APIs to work in software. Your classes take developers from a single request in a script to a backend service that streams replies, validates JSON against a schema and survives rate limits, and teach them to check token use, latency and error rates in their own logs.

The work

• Teach the live class “Get validated JSON from a model API with structured output and tool calls”, 90 minutes, from the class kit.
• Teach the live class “Stream, retry and track the cost of model API calls in a backend service”, 90 minutes, from the class kit.
• Show live how a JSON schema and a tool definition shape the response, how to validate it in code, and what to do when the output is cut off at the token limit.
• Walk learners through streaming tokens to a client, measuring time to first token, logging token counts per request and estimating what each feature costs to run.
• Help learners hit by 429 responses, timeouts or server errors, by adding retries with backoff and jitter, honoring retry‑after headers and keeping keys out of client code.

What to expect

• English is the class language, and learners from around the world attend live online. If you can teach in more languages, the application asks you to list them.
• Each class comes with a kit of slides, speaker notes, a minute‑by‑minute plan, a demo service that calls a model API, and a backup recording of the demo.
• You teach remotely on your own machine with a stable connection, a camera and a microphone, and an editor and terminal set up to run the demo service.
• Ahead of your first class, you pass that class's instructor test.
• Before a teaching assignment starts, you sign an instructor agreement. It covers pay, confidentiality and how class material may be used.
• Each invitation states the class times and the price learners pay, and you see both before you accept.

What you bring

• A service or integration you built on a model API in real work, with code or logs you can show.
• Experience teaching developers, writing technical tutorials, mentoring or running hands‑on coding sessions.
• Patience with backend developers meeting non‑deterministic output and usage‑based billing for the first time.

You need

• Hands‑on use of model APIs in production code: structured output, tool calling, streaming, retries and usage tracking.
• Backend experience in Python, TypeScript or a similar language, with HTTP, JSON and asynchronous requests.
• Fluent spoken English, the language the classes are taught in.
• 18 years or older.

Good to know

• Before you accept an assignment, get any approval for outside work that your employment contract requires.
• Teaching time depends on class demand, and you see the expected time commitment in each invitation before you reply.
• Nothing to pay to apply, and no YPAI Learn course you must buy or take.

Pay

$26–$99/hr. Rate shown is for the United States. This role is open in 4 countries, with local rates; pick your country on YPAI.

YPAI pays every two weeks for approved work via PayPal, Wise or bank transfer. Work is by invitation after your profile is reviewed.