Senior AI Software Engineer – Java, Spring Boot, Python

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

📋 Description

• Design, develop, and maintain backend services using Java, Spring Boot, Python, and FastAPI or similar frameworks.

• Create APIs and integrations for enterprise applications.

• Build solutions powered by LLMs utilizing OpenAI, Claude, Gemini, Llama, Azure OpenAI, or similar technologies.

• Design and implement Retrieval-Augmented Generation (RAG) based solutions.

• Develop backend services for managing prompts, context windows, token limits, response validation, and hallucination mitigation.

• Integrate AI services with enterprise platforms through REST APIs, JSON, asynchronous processing, and event-driven architectures.

• Design processes for transforming, normalizing, and preparing structured and unstructured data for AI solutions.

• Implement validation mechanisms, guardrails, error handling, logging, and monitoring for AI-driven applications.

• Evaluate the quality of responses generated by models using validation criteria, test cases, and review processes.

• Optimize the performance, reliability, concurrency, and scalability of backend and AI services.

• Utilize AI-assisted development tools to accelerate development, refactoring, testing, and documentation.

• Participate in code reviews, automated testing, CI/CD processes, and production deployments.

• Collaborate with Product, Architecture, and Engineering teams to develop scalable and production-ready solutions.

⛳️ Requirements

• Strong experience developing backend applications with Java and Spring Boot.

• Experience working with Python, particularly in backend services, AI integrations, automation, or data processing.

• Proven experience in developing REST APIs and backend services for production environments.

• Hands-on experience in developing or integrating applications based on Large Language Models (LLMs).

• Knowledge and experience in Retrieval-Augmented Generation (RAG), embeddings, vector databases, prompt engineering, context windows, token management, large input handling, chunking, output validation, and hallucination handling.

• Experience with one or more models such as OpenAI, Claude, Gemini, Llama, or Azure OpenAI.

• Knowledge in API design, JSON, data structures, concurrency, asynchronous processing, and system integration.

• Ability to develop clean, maintainable, scalable, and production-ready code.

• Experience utilizing AI-assisted development tools like Cursor, Claude Code, GitHub Copilot, or similar.

• Familiarity with Git, agile methodologies, and CI/CD processes.

• Desirable: experience with FastAPI or Flask.

• Desirable: experience with Pinecone, Weaviate, FAISS, Chroma, Azure AI Search, or other vector databases.

• Desirable: experience with semantic search, document parsing, retrieval tuning, and knowledge base integration.

• Desirable: experience building AI agents, tool calling, or LLM orchestration workflows.

• Desirable: experience with Docker, Azure, or cloud services.

• Desirable: experience with PostgreSQL, Redis, or similar technologies.

• Desirable: experience with pytest, JUnit, Playwright, or tools for API testing.

• Desirable: experience with event-driven architectures, processing queues, and background processes.

• Desirable: experience in enterprise, financial, regulated, or security-focused environments.

🏝️ Benefits

• Indefinite term contract.

• Full-time work schedule.

• Monday to Friday hours from 9:00 a.m. to 6:00 p.m. (Mexico time).

• Payment in Mexican pesos.