Senior GenAI RAG Engineer

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

📋 Description

• Develop and enhance AI Agents for deployment in production settings

• Design and implement architectures for Retrieval-Augmented Generation (RAG)

• Construct data pipelines for ingestion, processing, indexing, and retrieval

• Integrate Large Language Models (LLMs) with various systems, APIs, and enterprise platforms

• Optimize inference workflows to ensure high performance, scalability, and reliability

• Apply best practices regarding security, governance, and solution quality

• Collaborate on defining the technical architecture and advancing the AI platform

• Monitor, document, and drive continuous enhancements in the solutions

⛳️ Requirements

• Proven experience with Generative AI, LLMs, and developing AI Agents

• Experience in building RAG architectures

• Strong proficiency in Python programming

• Familiarity with LangChain, LangGraph, LlamaIndex, or similar frameworks

• Understanding of vector databases and techniques for embeddings, chunking, and semantic search

• Experience working with REST APIs, Git, and Docker

• Knowledge of cloud services such as AWS, Azure, or GCP

• Experience with CI/CD processes and deploying applications to production

• Understanding of security and governance measures for AI solutions

• Nice-to-have: experience with Azure OpenAI, Amazon Bedrock, or Vertex AI

• Nice-to-have: knowledge of LLMOps/MLOps and observability practices

• Nice-to-have: familiarity with Kubernetes, GraphRAG, MCP, and multi-agent systems

• Nice-to-have: proficiency in technical English

🏝️ Benefits

• Opportunity to work in a cutting-edge technology environment

• Collaborative team culture and professional development opportunities

• Flexible work arrangements and competitive compensation