Data Engineer – GenAI / LLM Engineering

Data Engineer GenAI / LLM Engineering

Location: Remote (Brazil or Argentina Preferred)

Region: Nearshore Latin America

Department: Machine Learning Engineering (MLE)

Overview

We are seeking an experienced Data Engineer with strong backend engineering experience to help build and scale enterprise Generative AI solutions. This role is focused on developing the data infrastructure, backend services, integrations, and pipelines that power LLM applications, AI agents, and Model Context Protocol (MCP)-based solutions.

This is not a traditional Data Science position. We are looking for an engineer who can operate at the intersection of data engineering, backend development, and AI infrastructure , enabling production-grade GenAI applications through scalable architecture and enterprise integrations.

Key Responsibilities

Design, build, and maintain scalable data pipelines supporting LLM, GenAI, and machine learning applications.

Develop backend APIs, services, and integrations connecting AI applications to enterprise data sources, tools, and platforms.

Build and maintain MCP servers and integrations enabling secure access to enterprise systems and services.

Support AI agent and agentic workflow development, including orchestration, tool integration, and data access.

Design secure integrations between LLM-powered applications and enterprise systems, including authentication, authorization, governance, and audit controls.

Build reliable ETL/ELT processes for structured and unstructured data used by AI applications.

Develop production-grade Python services and backend components.

Design scalable data models and retrieval patterns optimized for GenAI workloads.

Integrate with REST APIs, databases, cloud platforms, and enterprise applications.

Implement monitoring, logging, observability, security, and performance best practices.

Partner closely with ML Engineers, Software Engineers, Architects, and Product teams to move AI solutions from concept to production.

Participate in code reviews, testing, deployment, documentation, and ongoing production support.

Required Qualifications

Bachelor's degree in Computer Science, Engineering, Information Systems, or related field.

5+ years of experience in Data Engineering, Backend Engineering, or Software Engineering.

Strong proficiency in Python and SQL.

Experience designing and building scalable data pipelines and ETL/ELT workflows.

Strong backend development experience, including REST API design and system integrations.

Experience with Spark, Airflow, Argo, or similar data orchestration technologies.

Experience working within AWS and cloud-based data platforms.

Strong understanding of databases, data modeling, data warehousing, and distributed systems.

Experience with Git, CI/CD, testing frameworks, and production support.

Proven ability to build secure, reliable, and maintainable enterprise-grade systems.

GenAI / LLM Engineering Experience

Candidates should have hands-on experience with modern Generative AI environments, including:

Building or supporting MCP servers, clients, or integrations.

AI agents, agentic workflows, tool/function calling, and orchestration.

Integrating LLMs with enterprise data sources, APIs, databases, and backend systems.

Developing backend services that support GenAI and LLM-powered applications.

Working with structured and unstructured datasets in AI environments.

Familiarity with RAG architectures, embeddings, vector databases, and retrieval systems.

Preferred Qualifications

Experience delivering enterprise GenAI applications into production environments.

Experience with LangChain, LangGraph, Semantic Kernel, or related agent frameworks.

Familiarity with Azure OpenAI, Amazon Bedrock, OpenAI APIs, or similar LLM platforms.

Experience with Docker, Kubernetes, and containerized deployments.

Familiarity with microservices and event-driven architectures.

Experience in enterprise AI or Machine Learning Engineering organizations.

Understanding of AI governance, responsible AI, security, and access control practices.

Ideal Candidate

We are looking for an engineer who is comfortable moving beyond traditional ETL and analytics work. The ideal candidate can build the infrastructure, services, integrations, and data capabilities required for modern AI applications, while helping connect enterprise systems, APIs, tools, and data sources to LLM-powered solutions and AI agents in production environments.