Mercor Software Engineer Interview Experience — Applied AI Tech Screen with an Async Refund Debugging Question and Rapid-Fire LLM Questions

Today I had a tech screen for Mercor's Applied AI role.

The debugging question:

async def refund_money(request_id: str):
    refund = await get_db_record(request_id)
    if refund.status == "done":
        return
    for i in range(3):
        try:
            await stripe_api_call(
                refund.request_id,
                refund.amount
            )
            break
        except Error:
            continue
    await mark_db_as_done(request_id)

The other rapid-fire questions:

• What is idempotency, and why do we need idempotent operations?
• What is RAG, and how is it related to fine-tuning?
• How would you handle context limit exceeded in an LLM application?
• LLM calls are usually stateless. How would you make an LLM application stateful?
• How would you handle prompt injection in an AI agent system?
• Debug an async refund/payment function with retries and database state updates.
• What project are you currently leading?
• Why would you consider yourself the owner of that project rather than just a participant?