Summary

Responsibilities:

• Data Warehouse & Analytics: Design and build our analytical data warehouse architecture. Create data models that support business intelligence and reporting needs. Develop insights and dashboards that drive strategic decisions across the organization.
• Data Infrastructure & Pipelines: Maintain the foundational data architecture including ETL pipelines and our core database. Ensure clean data flow from source systems, build real-time streaming capabilities, and create the reliable data foundation that feeds both our analytics and AI systems.
• AI Systems & Evaluation: Build and improve our AI-powered features. Develop evaluation frameworks to measure AI performance, accuracy, and reliability. Create testing pipelines that ensure quality before deployment. Implement monitoring systems to track AI behavior in production and identify areas for improvement.
• AI Context & Integration: Create the knowledge systems our AI features need to understand each client's unique situation. Build retrieval systems for instant access to relevant information, develop semantic search capabilities, and structure data so our AI can provide personalized, contextual responses.

Must-have Qualifications:

• At least (2) years of hands-on experience in data engineering or AI/ML engineering
• Strong data modeling and data warehouse design skills
• Experience building business intelligence solutions and delivering data-driven insights
• Strong Python skills and experience with modern AI frameworks (LangChain, LlamaIndex, or similar)
• Experience building data pipelines and working with SQL databases
• Hands-on experience with LLMs, prompt engineering, or building AI-powered applications
• Self-directed mindset with strong ownership mentality

Nice-to-have Qualifications:

• Experience with modern data warehouse platforms (Redshift, Snowflake, BigQuery)
• Experience with testing and evaluation of AI/ML systems
• Proficiency with BI tools (Tableau, Looker, QuickSight)
• Experience with AI evaluation frameworks and metrics
• Experience with vector databases (Pinecone, Weaviate, ChromaDB)
• Background in building RAG systems or conversational AI
• Experience with AWS data stack (Redshift, Glue, S3, Lambda)
• Knowledge of embedding models and semantic search