AI Workflow Engineer Prompt Engineering

About OpenTrain

OpenTrain AI is the hiring and contracting organization for this role. OpenTrain is the #1 platform for finding and building careers in AI training and data labeling, helping people discover projects, build their profiles, and apply in minutes.

Creating an OpenTrain account is free. Through this contract opportunity, you can contribute to practical AI development while building experience in a fast-growing technology field.

• Remote contract opportunity
• Part-time schedule of 20+ hours per week
• Advertised hourly range of $15 to $45 USD

About AI Training and LLM Evaluation

AI training is the human side of building artificial intelligence. People help modern models improve by writing prompts, reviewing generated responses, applying evaluation criteria, and providing structured feedback that supports more reliable behavior.

This project focuses on large language model integrations, automation workflows, prompt engineering, and evaluation. Your work will help assess and refine how AI performs in practical communication, content generation, and personalized outreach scenarios.

• Work with cutting-edge large language model systems
• Review and rate model outputs for quality and reliability
• Apply human judgment to improve AI-generated content and workflows

The Role

As an AI Workflow Engineer, you will help integrate large language models into automation workflows and develop, test, and refine prompts and evaluation criteria. The role combines prompt engineering, LLM API integration, text evaluation, data structuring, and iterative quality improvement.

You will design real-world AI automation pipelines and improve model outputs through advanced prompting, input structuring, and repeated refinements. You will also review generated outputs for quality and reliability in tasks such as content generation, communication, and personalized outreach flows.

• Experience level: Intermediate
• Subject matter: LLM integrations and prompt engineering
• Work type: Contractor and part-time
• Workload: 20+ hours per week
• Data type: Text

What You’ll Do

You will work across the design and review stages of AI-powered automation. Responsibilities include building workflow concepts, shaping inputs, testing prompts, reviewing model behavior, and refining systems based on evaluation results.

The project includes evaluation, fine-tuning support, reinforcement learning from human feedback, function calling, and computer programming or coding-related workflow activities.

• Design and test prompts for large language model workflows
• Create and refine evaluation criteria and rubrics
• Evaluate LLM outputs for legal reasoning quality
• Integrate LLM APIs through REST APIs, SDKs, or automation tools
• Build AI-powered content automation for communication
• Structure data, create templates, and clean inputs
• Review generated outputs for quality, reliability, and limitations
• Use APIs, webhooks, and automation tools such as Zapier

Requirements

This role requires practical experience with LLM evaluation, prompt engineering, and AI workflow integration. Applicants should be comfortable assessing model outputs, working with structured inputs, and improving results through iterative prompt and workflow changes.

Applicants must submit a CV in English that indicates their level of English proficiency and includes an email address and phone number.

• Experience with text annotation, evaluation, or rubric-based quality assurance
• Strong prompt engineering experience, including instruction design, chaining, and structured outputs
• Experience integrating LLM APIs through REST APIs, SDKs, or automation tools
• Knowledge of LLM limitations and methods for mitigating them
• Experience building workflows with APIs, webhooks, or automation tools
• Ability to evaluate legal reasoning quality in LLM outputs
• CV submitted in English with English proficiency level, email address, and phone number

Who Should Apply

This opportunity is suited to an intermediate practitioner who combines technical workflow skills with careful evaluation and communication judgment. It may be a strong fit for someone experienced in prompt design, LLM output review, automation, or AI-powered content systems.

The project is worldwide in principle, but acquisition is restricted in the locations listed below. Applicants should review these restrictions before applying.

• Restricted countries and territories include Iran, Cuba, North Korea, Syria, Sudan, Venezuela, Myanmar, Russia, Belarus, Palestine, Switzerland, China, Taiwan, and Kenya
• Restricted U.S. states include Alaska, Arkansas, California, Connecticut, Delaware, Georgia, Hawaii, Illinois, Indiana, Kansas, Louisiana, Maine, Maryland, Massachusetts, Nebraska, Nevada, New Hampshire, New Jersey, New Mexico, Ohio, Oregon, Tennessee, Utah, Vermont, Washington, and West Virginia
• Additional restricted locations include Antarctica, Aruba, Åland Islands, Saint Barthélemy, Bonaire, Sint Eustatius and Saba, Bouvet Island, Cocos (Keeling) Islands, Democratic Republic of the Congo, Cook Islands, Christmas Island, Western Sahara, Falkland Islands (Malvinas), French Guiana, Guadelou

How to Apply

Apply through OpenTrain AI by creating a free account and submitting your application materials. Include an English-language CV with your English proficiency level, email address, and phone number.

If selected, you can contribute remotely to AI training work involving LLM evaluation, prompt refinement, automation workflows, and human feedback. The advertised compensation is $15 to $45 USD per hour, with a commitment of 20+ hours per week.

• Create a free OpenTrain account
• Submit your English-language CV and required contact details
• Confirm that your location is not subject to the stated acquisition restrictions
• Apply for the intermediate contractor opportunity