Head of Artificial Intelligence

Key Responsibilities

1. Lead AI Engineering for All New Product Experiences

• Own front-end engineering for all new products, especially those built around conversational, guided, or generative AI UX.
• Define the UI/UX architecture for the AI assistant, ensuring capabilities like:
• conversational task execution
• proactive insights
• AI-driven workflows
• cross-product navigation
• Oversee design system, component libraries, and UX patterns for AI-native interfaces.

2. Build and Operate All AI Pipelines

• Architect and maintain the pipelines required for:
• LLM orchestration
• RAG and retrieval systems
• embeddings generation
• vector storage
• agent pipelines
• supervised and RLHF evaluation loops
• Ensure pipelines support scale, latency needs, and multi-model routing.

3. Unified Model + API Architecture Using MCP

• Design and own the MCP-based layer that connects:
• models (LLMs, geospatial, POI, forecasting, classification, etc.)
• APIs (internal systems, external data sources, enrichment providers)
• workflows (Appian or bespoke orchestrators)
• Standardize how capabilities are registered, versioned, and exposed to the AI assistant.

modular, discoverable, and extensible.

4. End-to-End Ownership of AI Assistant Engineering

• Lead the engineering of all features that drive the assistant, including:
• intent recognition
• multi-step task planning
• tool selection + tool calling
• conversational memory + context
• guardrails and safety systems
• evaluation frameworks (automated and human-in-the-loop)
• Partner with Product and Data Science to continuously expand the assistant's capabilities.

5. Deep Partnership with Core Engineering

Work closely with the Core Engineering Leader to ensure:

• Clean, reliable data pipelines feeding RAG + model inputs
• Scalable cloud foundations for serving LLMs, vector DBs, and inference workloads
• AI workflows can trigger or orchestrate Appian-based processes
• Model outputs are productionized with strong monitoring and observability
• Front-end apps integrate smoothly with Core's services and data stores

AI builds the experiences; Core builds the substrate.

6. People Leadership & Organization Building

• Manage AI engineers, front-end engineers, and ML engineers developing AI capabilities.
• Build a high-performance culture across experimentation, engineering rigor, and responsible AI.
• Develop career paths, mentoring, and upskilling to support specialization in AI product engineering.

Qualifications

• 10+ years engineering experience including 35+ years in AI/ML engineering leadership.
• Deep expertise in LLM pipelines, RAG systems, vector search, model serving, observability, and evaluation.
• Strong background in building

  front-end user experiences

  , especially AI-native interfaces.
• Experience designing or using agent frameworks, tool-calling systems, or protocols similar to MCP.
• Proven ability to build highly reliable production systems with cross-functional dependencies.
• Ability to set clear architectural direction, simplify complexity, and drive alignment across engineering, product, and data science.

Success Criteria

• AI Assistant launched

  with stable, reliable, multi-tool capabilities.

• MCP architecture in place

  , with internal models and APIs connected via a unified interface.

• New AI-native product experiences

  shipped with measurable user adoption.

• Robust pipeline architecture

  supporting fast iteration across models and features.

• Strong engineering partnership

  with Core on data, cloud, and workflow foundations.

• Predictable release cadence

  for AI capabilities across GRO, POI, FIN, and new product lines.