AI Data Engineer III

Location: Remote, Brazil; minimal travel for occasional team meetings or training

Company

Global enterprise software support provider offering products and services for Oracle, SAP, Salesforce, AWS, and related business technology platforms.

What you will do

• Design and build production RAG pipelines for AI agents, including chunking, hybrid retrieval, query reformulation, reranking, and retrieval evaluation.
• Develop embedding and vector infrastructure with PostgreSQL and pgvector, including scalable processing, incremental indexing, multi-tenant isolation, and performance monitoring.
• Build ingestion and ETL pipelines for Salesforce, ServiceNow, SharePoint, Confluence, documentation, email archives, and ERP transaction data.
• Design knowledge architectures, graphs, taxonomies, versioning strategies, and feedback loops for enterprise ERP knowledge.
• Integrate operational systems, Snowflake, and vector stores while maintaining data isolation, lineage, synchronization, and cost efficiency.
• Collaborate with GenAI engineers and technical and non-technical stakeholders to diagnose pipeline issues and optimize agent knowledge access.

Requirements

• 5+ years of data engineering experience, including 1–2 years focused on AI/ML data pipelines or RAG systems.
• Production experience with RAG pipelines, vector databases, embeddings, similarity search, retrieval optimization, and reranking.
• Strong Python, PostgreSQL, SQL, data modeling, ETL/ELT, and pipeline orchestration skills.
• Experience with pgvector or comparable vector databases such as Pinecone, Qdrant, or Weaviate.
• Experience with Git, CI/CD, REST or GraphQL API integration, and relational and document-oriented data processing.
• Fluent English is required; the role is restricted to candidates based in Brazil.

Nice to have

• Experience with Snowflake and Cortex AI, embedding models, LlamaIndex, LangChain, or Haystack.
• Knowledge of PDF extraction, HTML parsing, OCR, Salesforce or ServiceNow APIs, knowledge graphs, and graph databases.
• Experience with data quality frameworks, dbt, Elasticsearch, OpenSearch, or LLM fine-tuning and training data preparation.
• Enterprise software, ERP, support systems, or B2B SaaS experience.

Culture & Benefits

• Remote work with minimal travel requirements.
• Work focused on enterprise AI, agent intelligence, and meaningful customer-facing solutions.
• Culture centered on innovation, collaboration, client service, and community impact.
• Compensation, bonuses, and benefits aligned with skills and performance.
• Inclusive workplace with equal employment opportunity principles.