AI Engineer

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

📋 Description

• Create and develop reusable components, libraries, APIs, plugins, and tools that facilitate AI integration across products and engineering teams.

• Incorporate AI functionalities into the internal development framework, ensuring ease of adoption for engineering teams.

• Establish reference architectures, technical patterns, standards, and best practices for solutions based on Generative AI.

• Design and execute integrations with Large Language Models and AI services, primarily within the AWS environment.

• Produce production-ready solutions using Node.js, TypeScript, serverless architectures, and the Serverless Framework.

• Investigate and apply structured generation, tool calling, agents, RAG, MCP, embeddings, and semantic search.

• Establish testing and evaluation frameworks to ensure quality, security, latency, reliability, and cost-effectiveness of AI-driven solutions.

• Implement observability for model usage, prompts, tokens, responses, errors, execution times, and other critical operational metrics.

• Set up technical controls and engineering practices to ensure secure and responsible usage of AI technologies.

• Develop proof-of-concepts and evolve effective strategies into scalable, maintainable, production-ready solutions.

• Generate technical documentation, implementation examples, and guidelines for adoption.

• Assist development teams in utilizing reusable AI components, architectures, and engineering best practices.

• Engage in architecture reviews and contribute to technical decision-making processes.

• Disseminate knowledge and advocate for AI engineering best practices.

⛳️ Requirements

• Extensive experience at a senior level in backend software development.

• Strong proficiency in Node.js and substantial experience with JavaScript and/or TypeScript.

• Practical experience with AWS, serverless architectures, and distributed systems.

• Proven track record in designing and developing APIs, libraries, frameworks, plugins, or other reusable software components.

• In-depth understanding of software design principles and engineering best practices, including testing, security, observability, and CI/CD.

• Experience contributing to software architecture, technical design, and engineering decision-making processes.

• Hands-on experience in developing or integrating solutions leveraging Large Language Models (LLMs) and Generative AI.

• Capability to translate business and technical requirements into scalable, generic, and reusable solutions.

• Ability to research new technologies, assess alternatives, and convert concepts and proof-of-concepts into production-ready solutions.

• Self-motivated with a strong sense of ownership and independence.

• Excellent communication skills, technical documentation abilities, and proficiency in cross-team collaboration.

• Familiarity with Amazon Bedrock or other Generative AI platforms.

• Experience with the Serverless Framework and plugin development.

• Practical knowledge of RAG, AI agents, tool calling, Model Context Protocol (MCP), structured generation, embeddings, and semantic search.

• Familiarity with AWS services such as Lambda, API Gateway, Step Functions, EventBridge, SQS, SNS, and DynamoDB.

• Understanding of vector databases and technologies related to semantic search.

• Experience in implementing evaluation frameworks, guardrails, observability, and operational practices for applications based on LLMs.

• Background in building internal development platforms, frameworks, or tools for developers.

🏝️ Benefits

• Equal opportunities in recruitment, career advancement, and leadership roles.

• A diverse and inclusive workplace environment.