Full-Stack Developer - AI+ ML + Backend + RAG (LATAM)

About the Role

We’re looking for a highly skilled Full-Stack AI Developer with strong experience in Machine Learning, RAG pipelines, and backend integration. You’ll help us process large datasets, build AI-powered features, and integrate ML models into our backend (Python/Node.js) and eventually our React frontend.

This is not just prompt work — we need someone who has hands-on experience building ML systems, not only using APIs.

Responsibilities

Machine Learning & AI Work

Build, train, and optimize ML models for processing large datasets.

Develop Retrieval-Augmented Generation (RAG) pipelines to pull manuals, images, and other relevant information based on user prompts.

Use LLM techniques to cross-reference, validate, and improve system outputs.

Implement embeddings, vector search, and data retrieval workflows.

Backend Integration

Integrate ML and RAG pipelines into backend services (Node.js/Python).

Build clean and scalable backend endpoints to support AI-driven features.

Work with databases (Supabase, PostgreSQL, or similar) to manage structured and unstructured data.

Collaboration & Delivery

Work independently and proactively, communicating clearly during EST business hours.

Collaborate with team members on architecture, performance improvements, and new feature ideas.

Requirements

Strong Python experience with ML frameworks (TensorFlow, PyTorch, or similar).

Proven experience building RAG systems, embedding pipelines, or retrieval workflows.

Hands-on experience training or fine-tuning ML models.

Solid understanding of LLM behavior, prompt engineering, and data preprocessing.

Comfortable developing backend services in Node.js and working with APIs.

Ability to work independently, troubleshoot issues, and propose solutions.

Nice to Have

Experience with high-volume or real-time data systems.

Experience integrating AI features into React applications.

Familiarity with Supabase, Cloudflare, or edge-based architectures.

To Apply — Please Answer These Questions

Briefly describe a project where you built or fine-tuned an ML model.

Have you built a RAG pipeline before? If yes, describe your approach and tools.

What ML and backend tools/frameworks are you most comfortable with?

About Sail Onyx

Sail Onyx is a fast-growing leader in premium yacht restoration and maintenance. We combine craftsmanship with cutting-edge technology to modernize and elevate the service experience. We are expanding and looking for proactive, detail-oriented team members excited to innovate with us.