Full-Stack Engineer, AI, LLM Integration

This is a fully remote position, open to applicants in Mexico.

📋 Description

• Refine, reorganize, and modularize a rapid-prototype frontend built with React/Next.js.

• Design and create a robust backend architecture suitable for production from the ground up.

• Transition direct LLM API calls into a well-structured orchestration layer.

• Construct and enhance advanced workflows for prompt engineering and image generation pipelines, particularly utilizing OpenAI's image generation models/DALL-E.

• Establish data ingestion workflows to interpret clinical study protocols.

• Organize and prepare internal ad-performance training data for potential fine-tuning of LLMs.

• Take ownership of the deployment, hosting, and monitoring strategy to evolve the app from a fragile prototype to a reliable, scalable MVP.

• Adhere to best practices for data management (Note: the application processes study protocols and marketing data, not patient data/PHI; therefore, full HIPAA/SOC 2 compliance is not mandated for this phase).

⛳️ Requirements

• A minimum of 4 years of professional experience in full-stack development, confidently operating at a strong Mid to Senior level.

• Profound knowledge of React and Next.js.

• Proven experience in constructing production-quality backends (Node.js) and deploying applications to stable cloud environments.

• Practical experience in integrating LLMs, managing image generation pipelines, addressing API rate limits, and implementing orchestration frameworks (such as LangChain, LlamaIndex, or custom structured outputs).

• A resourceful yet disciplined engineer who is willing to tackle messy, auto-generated code and systematically refactor it while maintaining progress.

🏝️ Benefits

• Opportunity to work on cutting-edge technology in a dynamic environment.

• Collaborate with a talented team of professionals.

• Flexible working arrangements to promote work-life balance.

• Competitive salary and potential for growth within the company.