Senior LLM Engineer (RAG & AWS Bedrock)

Team: Python Engineer

Location: São Paulo, Greater Fortaleza, Rio de Janeiro, Rio de Janeiro, Brazil, Florianópolis, Santa Catarina, Brazil, Mexico City, Buenos Aires Province, Bogota,D.C., Capital District

Commitment: Remote

Workplace Type: remote

About the Role

We are looking for an experienced Senior LLM Engineer to build an AI-powered data intelligence platform that enables users to interact with multiple enterprise data sources through natural language.

This role focuses on designing and implementing Retrieval-Augmented Generation (RAG) solutions, semantic search, and conversational AI experiences powered by AWS Bedrock. You will build scalable AI pipelines capable of retrieving, processing, and synthesizing information from multiple structured and unstructured data sources into an intuitive chatbot experience.

The ideal candidate has strong experience building Generative AI applications, designing RAG architectures, and working with vector search, embeddings, and cloud-native AI services.

Key Responsibilities:

• Design and implement Retrieval-Augmented Generation (RAG) architectures.
• Build AI-powered chatbot experiences using AWS Bedrock.
• Develop multi-source data ingestion and retrieval pipelines.
• Design and optimize embeddings and semantic search strategies.
• Build scalable vector search solutions for enterprise knowledge retrieval.
• Integrate structured and unstructured data sources into AI workflows.
• Develop prompt engineering strategies to improve response quality and accuracy.
• Build cloud-native AI services using AWS.
• Collaborate with engineering teams to improve AI performance, scalability, and reliability.
• Continuously evaluate new AI technologies and best practices for enterprise LLM applications.

Requirements:

• 5+ years of professional software engineering experience.
• Strong Python development experience.
• Hands-on experience building Generative AI applications.
• Experience working with AWS cloud services.
• Strong understanding of Retrieval-Augmented Generation (RAG).
• Experience building scalable backend applications.
• Strong analytical and problem-solving skills.
• Experience working in Agile environments.
• Strong written and verbal English communication skills.

Must Have:

• Strong Python development experience.
• Hands-on experience with AWS Bedrock.
• Experience building Retrieval-Augmented Generation (RAG) solutions.
• Experience working with:
  • Embeddings
  • Vector Search
  • Semantic Search
  • Experience building AI-powered chatbot applications.
  • Experience designing multi-source data ingestion pipelines.
  • Experience working with S3 Data Lakes.
  • Strong Prompt Engineering experience.
  • Experience integrating multiple enterprise data sources.
  • Strong understanding of Large Language Models (LLMs).
  • Experience designing scalable AI architectures.

Nice to Have:

• Experience with:
  • LangChain
  • LlamaIndex
  • Pinecone
  • Weaviate
  • OpenSearch Vector
  • ChromaDB
  • FAISS
  • Experience building conversational AI applications.
  • Experience with enterprise knowledge management systems.
  • Experience with API Gateway.
  • Experience with EventBridge or SQS.
  • Experience with Infrastructure as Code.
  • Experience optimizing LLM performance and retrieval quality.
  • Experience with connected TV (CTV), AdTech, or advertising analytics platforms.