Staff AI Engineer, Data Ontologist

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

📋 Description

• Create and execute context architectures that empower AI systems to access, interpret, and reason over enterprise knowledge.

• Develop and sustain ontologies, schemas, and knowledge representations that organize domain knowledge across various systems, ensuring consistency, reusability, and scalability.

• Define and enhance context assembly pipelines, including retrieval strategies, ranking logic, memory management, and prompt/context composition for LLM-based systems.

• Construct and oversee semantic layers over both structured and unstructured data, facilitating effective grounding of AI agents in real-world business contexts.

• Design and implement knowledge graphs and context graphs to illustrate relationships among entities, actions, and outcomes across enterprise systems.

• Collaborate with AI Engineers and Data teams to synchronize embeddings, chunking strategies, and vector storage with ontology and semantic design.

• Establish standards for context quality, including evaluation frameworks for relevance, coherence, completeness, and business impact.

• Facilitate interoperability across AI systems by defining shared context interfaces, schemas, and protocols (e.g., MCP or API-based context services).

• Continuously improve context systems based on agent performance, feedback loops, and operational insights.

• Transform complex semantic and contextual concepts into actionable implementations for both technical and non-technical stakeholders.

⛳️ Requirements

• Extensive experience in designing semantic systems, ontologies, or knowledge graphs within intricate data environments.

• Practical experience with knowledge representation techniques, including taxonomy design, entity-relationship modeling, and graph-based structures.

• Experience with LLM-based systems, particularly in context engineering, retrieval-augmented generation (RAG), or agentic AI architectures.

• Profound understanding of embeddings, vector databases, and retrieval strategies, and their interactions with structured semantic layers.

• Experience in designing context pipelines that integrate multiple data sources (APIs, databases, documents) into cohesive inputs for AI systems.

• Familiarity with frameworks and tools related to graph databases (e.g., Neo4j), semantic layers, or metadata management.

• Strong comprehension of trade-offs in context construction, including latency vs. completeness, precision vs. recall, and static vs. dynamic context.

• Experience in cloud environments (AWS, Azure, GCP) and integrating AI systems into production-grade architectures.

• Ability to convey complex semantic and AI concepts clearly to both technical and business stakeholders.

🏝️ Benefits

• Health and dental plan

• Life insurance

• Monthly voucher for meals, culture, education, health, and mobility

• Child care assistance and more!