Low-Code Developer, Automation & JavaScript

About OpenTrain

OpenTrain is the #1 platform for finding and building careers in AI training and data labeling. We help people start and grow careers teaching AI by connecting contributors with training projects, building reviewer skills, and enabling flexible remote work.

• Work remotely and shape how real AI systems behave.
• Flexible, part-time contractor projects you can fit around other commitments.

About AI training work for this role

AI training (data labeling, annotation, and human feedback) is the human side of building modern models. In this role you'll combine low-code workflow engineering with language-model evaluation: creating and reviewing multi-step prompts, assessing AI-generated solutions, and producing high-quality evaluation labels used for RLHF, fine-tuning, and model validation.

• Hands-on work contributes directly to model behavior and reliability.
• Tasks mix technical workflow design, JavaScript logic, and rubric-driven annotation and QA.

The role

We're seeking an experienced low-code developer to design, build, and evaluate advanced automation workflows and logic for AI training. You will create production-grade flows (Make.com and/or n8n), write custom JavaScript for advanced logic and error handling, and evaluate LLM outputs for correctness and legal reasoning quality where required.

• Employment type: Contractor, Part Time.
• Time commitment: 20+ hours per week.
• Pay model: Paid per hour (USD). Hourly range $15–$45; posted hourly rate $45.

What you'll do

Work across automation platforms and language models to produce reliable, scalable workflows and high-quality evaluation data.

• Design and implement multi-step automation workflows using Make.com and/or n8n in production.
• Write custom JavaScript to implement advanced logic, error handling, retries, and performance optimizations.
• Integrate APIs and webhooks, manage authentication, rate limits, and cross-app data flow.
• Create and assess multi-step prompts and model responses; apply rubric-based QA for evaluation and fine-tuning data.
• Perform RLHF-style evaluations and assign evaluation ratings to model outputs, including functional-calling/code-correction tasks.
• Review AI-generated automation solutions and propose fixes to improve reliability and scalability.

Requirements

You must preserve these base qualifications exactly as stated. Applications that do not address the listed requirements may not be considered.

• Proven hands-on experience building production workflows with Make.com and/or n8n.
• Strong JavaScript skills for custom logic, error handling, and performance tuning.
• Experience integrating multiple apps via APIs and webhooks, including auth and rate-limit handling.
• Experience designing multi-app automation and optimizing workflow performance.
• Hands-on text annotation, evaluation, or rubric-based QA experience.
• Experience evaluating LLM outputs for legal reasoning quality (ability to assess legal-style reasoning).
• CV must be in English and indicate your English proficiency level; include an email address and phone number.

Location, eligibility, and additional details

This is a worldwide contractor role but acquisition is restricted in certain countries and territories. Candidates located in the restricted list cannot be acquired for this project.

• Restricted locations for acquisition: Iran, Cuba, North Korea, Syria, Sudan, Venezuela, Myanmar, Russia, Belarus, Palestine; Switzerland; China, Taiwan; Kenya; States of the USA: Alaska, Arkansas, California, Connecticut, Delaware, Georgia, Hawaii, Illinois, Indiana, Kansas, Louisiana, Maine, Maryla
• You will work primarily with text data and tasks include evaluation rating, fine-tuning data, RLHF, programming/coding evaluation, and function-calling labels.

How the process works

Apply with the requested CV details; candidates who meet technical and eligibility checks will receive onboarding instructions, training materials, and rubric documentation. Work is delivered remotely via OpenTrain's project tools and follows the project's labeling and QA guidelines.

• Onboarding includes sample tasks, a qualification quiz, and rubric calibration.
• Ongoing work is assigned as batches or tasks; expect to review and correct model outputs and submit annotated labels per rubric.
• Payment is hourly; timesheets or task-logs may be required per project.

How to apply

Submit your CV in English and clearly state your English proficiency level. Include an email address and phone number. In your application, highlight your experience with Make.com and/or n8n, JavaScript automation logic, API/webhook integrations, and any prior annotation or LLM-evaluation work—especially legal-reasoning evaluations.

• Be explicit about recent production projects and the role you played (design, implementation, troubleshooting).
• List relevant labeling or QA projects and any rubric-based evaluation experience.