AI Engineer

About Datifact Datifact is The GenBI Company. Datifact builds the data, ontology and context layers that make enterprise AI work for mid-market companies (50 to 500 employees, $10M to $250M in revenue), then delivers applications on top of them through QubeAI™, its AI-native operating system for the business. Most companies trying AI hit the same wall: their data is scattered, undefined and disconnected from how the business actually runs. Datifact solves that problem at the foundation. The platform is organized in four layers (Data, Ontology, Context, Application), and the engineer in this role will shape every one of them. Datifact is headquartered in Orange County, California, with a presence in Nashville, Tennessee. The Role Datifact is hiring an AI Engineer to design and build the data architecture, ontologies and LLM systems behind every client deployment. This role reports directly to the Chief Technology Officer and is one of the first engineering hires on the team. This is a builder's seat. The work spans modeling a client's business as a semantic layer, wiring real systems into a clean data foundation, and shipping LLM agents that reason over that context in production. Architecture decisions made in this role will become the blueprint Datifact repeats across every new account. Title: AI Engineer Reports to: Chief Technology Officer Type: Full time, salaried

Location:
Orange County, CA or Nashville, TN preferred; remote considered for the right candidate What You Will Do Data architecture Design and build client data foundations: ingestion pipelines, warehouse and lakehouse models, and integrations with ERP, CRM, accounting and operational systems (QuickBooks Online, Salesforce, Snowflake and similar) Own data modeling standards, schema design and data quality across multi-tenant environments Build ingestion for unstructured sources (documents, contracts, email, call notes) and turn them into structured, queryable context Make security, tenant isolation and access control first-class parts of every architecture Ontology and semantic layer Model how a business actually works: entities, relationships, metrics, rules and processes, expressed as an ontology an AI system can reason over Build and maintain reusable domain packs (Finance and Operations, Procurement, Sales, Customer Success) and industry overlays that accelerate every new deployment Define a governed semantic layer so every metric means one thing, everywhere, for every user and agent Work directly with client finance and operations leaders to translate how they run the business into models LLM and agent development Build production LLM applications and agents that retrieve, reason and act over client data and context Design retrieval systems (vector, graph and hybrid), prompt and context strategies, and tool-calling workflows Build evaluation harnesses that measure accuracy, grounding and reliability, and use them to drive every release Optimize for cost, latency and quality across frontier and small language models Ship to production and own what ships: monitoring, observability and iteration based on real usage Team and platform Partner with the CTO on platform architecture and technical roadmap Work alongside solutions engineering and client delivery on discovery, builds and managed services Document patterns so the team can repeat them, and help shape engineering culture as Datifact grows What You Bring 5+ years in data engineering, data architecture or ML engineering, with at least 2 years building LLM applications in production Deep experience designing data models and pipelines in modern platforms (Snowflake, Databricks, BigQuery, Postgres or similar) and strong SQL Hands-on ontology or semantic modeling

experience:
knowledge graphs, semantic layers, metrics layers or formal domain models (RDF/OWL, property graphs, dbt Semantic Layer, Cube or comparable) Proven work with LLM APIs and frameworks, retrieval-augmented generation, embeddings, vector databases and agent tool calling Strong Python; TypeScript a plus Experience building evaluations for LLM systems and using them to make decisions Cloud experience (Azure, AWS or GCP), including security, identity and multi-tenant design The judgment to choose the simple solution that ships over the clever one that does not Clear communication with non-technical executives; comfortable in a room with a CFO Startup ownership: you take a problem from blank page to production without waiting for a spec Nice to Have Background in finance, operations or business intelligence data (GL, AP/AR, inventory, sales pipeline) Experience fine-tuning or deploying small language models Graph databases (Neo4j, Neptune) or graph-based retrieval Supabase, pgvector or similar Postgres-native AI tooling Voice or multimodal agent experience Prior work in consulting, professional services or client-facing delivery Open source contributions or published work on semantic modeling, RAG or agent syste