Databricks Genie Architect
About Entrada AI
Entrada AI is a specialized consulting partner and a strategic portfolio company of Databricks Ventures. We were recently named the Genie Partner of the Year (2026) for our work deploying Databricks Genie at enterprise scale—bridging the gap between AI ambition and the trusted, governed data required for accurate responses. With over 150 Databricks projects delivered, we unlock self-service analytics for Fortune 500 leaders.
Databricks invested in us because of our technical excellence, placing us in the "inner circle" of the ecosystem. For our engineers, this means direct access to product roadmaps, private previews, and the teams building the platform. You will join a team of industry veterans who value clean architecture over quick fixes. We don't just maintain pipelines; we solve complex architectural challenges.
About the Role
As a Databricks Genie Architect , you will be the driving force behind building next-generation conversational data interfaces. Your primary focus will be designing, implementing, and scaling intelligent, natural-language data assistants using Genie .
You will bridge the gap between complex enterprise data warehouses and business users, enabling them to query databases using natural language. This role is a hybrid of cutting-edge Generative AI engineering and robust Data Engineering within the Databricks Lakehouse ecosystem.
Key Responsibilities
1. Databricks Genie & Conversational AI Development (Core Focus)
-
Genie Space Architecture: Design, configure, and maintain high-performing Databricks Genie Spaces tailored to complex business domains.
-
Semantic Layer & Curation: Curate the semantic metadata, SQL queries, and golden instructions that guide Genie to ensure highly accurate, deterministic SQL generation.
-
Testing & Fine-Tuning: Proactively test, benchmark, and fine-tune Genie responses to handle complex business logic, edge cases, and multi-turn conversations.
-
Integration & Feedback: Connect Databricks Genie endpoints to custom web interfaces/external UIs and implement feedback loops to continuously improve accuracy.
2. GenAI & Data Engineering Support
-
Data Pipelines & Spark: Build and optimize data pipelines using Python, SQL, and PySpark to ensure data in Delta Lake is perfectly structured and optimized for Genie's consumption.
-
GenAI Orchestration: Utilize LLMs on Databricks for metadata enrichment, automated data labeling, and semantic optimization.
3. Collaboration & Implementation
-
Business Translation: Act as a translator between business users (understanding what questions they ask) and the data platform (structuring schemas so Genie can answer them easily).
Technical Requirements
MUST HAVE
-
Databricks Mastery: 5+ years hands-on experience with the Databricks ecosystem, with specific focus on Databricks Genie (or equivalent Text-to-SQL/semantic-layer work) , Unity Catalog , and Databricks SQL/Workflows.
-
Excellent SQL & Data Modeling: Expert-level SQL skills (writing complex, performant queries) and experience structuring data (star schemas, gold tables, views) to be "Genie-ready."
-
Production Python: Strong experience in writing clean, production-grade Python code.
-
GenAI / LLM Concepts: Strong understanding of Text-to-SQL paradigms, prompt engineering, semantic routing, and RAG architectures.
-
Big Data: Proficiency in Apache Spark (PySpark) for data transformation and orchestration.
-
API Integration: Experience working with REST APIs to integrate GenAI endpoints into external applications.
NICE TO HAVE
-
MLflow & Model Serving: Manage model lifecycles and deploy endpoints utilizing the broader Databricks AI suite (MLflow, Databricks Model Serving).
Soft Skills
-
Analytical & Precise: Strong attention to detail, especially when auditing Genie's generated SQL for business accuracy.
-
Bridge Builder: Ability to communicate effectively with business stakeholders to understand their la