You’ll join a team building an ecosystem of AI agents to automate knowledge-intensive workflows, from processing content at scale to generating insights from diverse data sources. The solution combines a modern lakehouse data platform with agentic AI and advanced knowledge modeling. The architecture is still evolving, and we’re looking for a senior engineer to help shape it—someone who brings ideas, challenges assumptions, and takes ownership from technical decisions through delivery. We value a pragmatic, technology-agnostic approach. As the GenAI landscape evolves, you’ll evaluate tools based on their strengths and fit for the problem, keeping an open mind about new approache   Responsibilities    AI Architecture & Technical Ownership → Shape the architecture of GenAI solutions by proposing approaches, evaluating trade-offs, and co-owning technical decisions with the team, from initial design through production delivery AI Agent Development & Orchestration → Design, build, and orchestrate AI agents for data collection, indexing, and market intelligence, integrating LLMs, prompts, and tools into reliable end-to-end workflows Data Engineering & Lakehouse Development → Develop and maintain data pipelines and lakehouse structures in Databricks, supporting the ingestion, transformation, and organization of structured and unstructured data for AI-driven applications Knowledge Modeling & Ontology Development → Contribute to the knowledge-modeling layer by building ontologies that organize domain concepts and relationships, providing context to ground agent reasoning Agent Integration & Databricks Connectivity → Integrate AI agents with Databricks data and capabilities, evaluating approaches such as Genie and custom agent frameworks while helping define the integration architecture Python Development & Web Data Extraction → Build and maintain robust Python components for web scraping, content extraction, and indexing, ensuring reliable data collection and maintainable code Technical Evaluation & Continuous Improvement → Assess tools, frameworks, and implementation approaches; identify and drive improvements across the architecture, codebase, and engineering practices as the solution evolves Technical Collaboration & Knowledge Sharing → Work closely with the team through brainstorming, design reviews, and delivery; communicate technical decisions, challenge assumptions constructively, and share implementation insights