AI Prompt Engineer

Position: AI Prompt Engineer (Remote)

Employment Type: Contractor

Experience Required: 3+ years

Engagement Length: 6 Weeks (5 days working)

Role Overview

This position is within a project with one of the foundational LLM companies. The goal is to assist these foundational LLM companies in enhancing their Large Language Models (LLMs).

One way we help these companies improve their models is by providing them with high-quality proprietary data. This data serves two main purposes:

As a basis for fine-tuning their models

As an evaluation set to benchmark the performance of their models or competitor models

For example, in the case of Agent Completion (AC) data generation, your task will be to simulate high-quality multi-turn conversations between a user and a smart assistant that utilizes function-calling tools to accomplish user goals.

You will craft these dialogues by playing both the assistant and the user, while simulating tool use where necessary to guide the assistant through complex decision-making and real-world reasoning scenarios.

What Does the Day-to-Day Look Like

Design multi-turn conversations that simulate real interactions between users and AI assistants using apps like Calendar, email, maps, and Drive

Emulate both the user and the assistant, including the assistant's tool calls(only when corrections are needed)

Carefully select when and how the assistant uses available tools, ensuring logical flow and proper usage of function calls

Craft dialogues that demonstrate natural language, intelligent behavior, and contextual understanding across multiple turns

Generate examples that showcase the assistant's ability to:

Gracefully complete feasible tasks

Recognize infeasible tasks

Maintain engaging general chat when tools aren't required

Ensure all conversations adhere to defined formatting and quality guidelines, using an internal playbook

Iterate on conversation examples based on feedback to continuously improve realism, clarity, and training value

Collaborate with peers and reviewers to maintain consistency and high standards in deliverables

Requirements

Strong general technical reasoning skills and the ability to model real-world assistant behavior using tool-based APIs

Ability to break down complex tasks and simulate realistic dialogues that reflect user expectations and assistant limitations

Experience in any programming language or tech stack is acceptable

Strong understanding of APIs, data formats (e.g., JSON), and logical thinking

Excellent written communication skills in English, with clarity, tone, and instructional coherence

Creativity and attention to detail in crafting realistic scenarios and responses

Experience working with LLMs, virtual assistants, or function-calling frameworks(preferred)

Ability to follow detailed guidelines and formatting standards with high consistency.

Note:

1. Applications will only be accepted through the ATS link provided above. Profiles shared through other means will not be considered.

2. Prolegion does not charge any fee from candidates at any stage. If anyone approaches you for money in exchange for this opportunity, treat it as fraud and report it to us immediately.