Principal Data Scientist - Knowledge Engineering, Customer Sucess Data Platform

Intuit; San Diego (CA); Presencial; USD 248 000 - 335 000; Tempo integral

Resumo da oferta

Intuit Customer Success seeks a Principal Knowledge Engineer to architect and govern our enterprise knowledge foundation, including the Knowledge Graph. You will guide data scientists, engineers, and product teams, while staying close enough to code to prototype and unblock.

You will define semantic layers, govern data quality and provenance, and drive architecture decisions across graphs, retrieval, and AI experiences. This role balances business impact with long-term strategy.

Qualificações

• 15+ years in data and knowledge engineering or AI/ML with leadership on large-scale platforms.
• Experience shipping enterprise knowledge graphs or semantic platforms in production.
• Deep knowledge of ontology, taxonomy, entity resolution and knowledge graph construction.
• Hands-on with LLM-powered and agentic systems including retrieval and evaluation.

Responsabilidades

• Define and own the agentic knowledge architecture for ICs data platform and knowledge graph.
• Architect the agentic intelligence layer including GraphRAG, hybrid retrieval and memory.
• Set semantic layer strategy to express metrics and definitions consistently.
• Lead data and knowledge governance for quality, provenance, access control, and responsible AI.
• Decide on graph stores, vector stores, and tooling; document tradeoffs.
• Prototype reference implementations and contribute production code.
• Balance short-term business needs with long-term architecture.
• Define evaluation frameworks for knowledge coverage and retrieval quality.
• Translate business needs into architecture and build alignment.
• Guide and grow the team of data scientists, analysts and engineers.

Conhecimentos

Data engineering

Knowledge graphs

LLM-powered systems

Graph databases

RAG/GraphRAG

Context engineering

Distributed systems

Software development

Mentoring

Communication

Formação académica

BS in CS/DS

MS or PhD preferred

Ferramentas

LangGraph

LlamaIndex

MCP

Neo4j

Neptune

Databricks

Snowflake

Descrição da oferta de emprego

Intuit Customer Success is building the knowledge and agentic intelligence foundation that will power how millions of customers get help and how our teams make decisions based on knowledge and data. We’re looking for a hands‑on Principal Knowledge Engineer to be the architect of that data and knowledge foundation.

You will define and own the knowledge architecture and governance for the ICs data platform and agentic intelligence layer, including the Intuit Customer Success Knowledge Graph. Your work will power use cases such as internal customer success agent experiences and self‑serve data agents that let teams ask questions in plain language and get trusted answers. This is a rare chance to set the architecture and system for an enterprise‑scale agentic intelligence platform from the ground up. You will guide a team of data scientists, data professionals, and engineers, and you will stay close enough to the code to build, prototype and unblock.

Responsibilities

• Own the agentic knowledge architecture.Define the target architecture for how ICs knowledge is modeled, stored, connected and served to agents and people. This covers the Intuit Customer Success Knowledge Graph, ontologies and taxonomies, entity resolution, and how structured data, unstructured content and expert knowledge come together.

• Architect the agentic intelligence layer.Set the patterns for how agents retrieve, reason over and act on knowledge. This includes GraphRAG and hybrid retrieval (graph, vector and structured queries), context engineering, tool and MCP design, multi-agent orchestration, and memory.

• Set the semantic layer strategy.Define how business metrics, entities and definitions are expressed once and reused across dashboards, data agents and AI experiences. The goal is that “what does this number mean” has one answer everywhere.

• Lead data and knowledge governance.Build the governance strategy for knowledge quality, freshness, lineage, provenance, access control and responsible AI. Make sure agents answer from trusted, compliant and well‑attributed sources.

• Make the key architecture and tooling decisions.Evaluate and select graph stores, vector stores, semantic layer tools, agent frameworks and evaluation tooling. Make clear build-versus-buy calls and document the tradeoffs.

• Build hands‑on.Prototype reference implementations, write production-quality code, review designs and pull requests, and step into the hardest technical problems yourself.

• Balance now and next.Deliver what the business needs this quarter, such as tax‑season readiness and high‑impact self‑serve use cases. Make sure each delivery moves toward the long‑term architecture instead of adding technical debt.

• Define how we measure quality.Set the evaluation frameworks for knowledge coverage, retrieval quality, answer accuracy, groundedness and agent reliability, and use them to drive prioritization.

• Translate between business and technology.Work with segment data leaders, business, engineering, and operations to understand their workflows, nuances and decisions. Explain architectural choices in business terms and build alignment across teams.

• Guide and grow the team. Mentor data scientists, technical data analysts, and engineers. Raise the technical bar through design reviews and standards, and build a strong knowledge engineering practice across ICs.

Qualifications

Required

• 15+ years in data and knowledge engineering, or AI and ML engineering, including significant time as a technical lead or architect on large‑scale data or knowledge platforms.

• A track record of architecting and shipping large‑scale data and knowledge systems in production, such as enterprise knowledge graphs, semantic platforms, or data platforms that serve many teams and use cases.

• Deep expertise in knowledge modeling, including ontology and taxonomy design, entity resolution, graph data modeling and knowledge graph construction. This includes using LLMs for extraction and enrichment.

• Hands‑on experience building LLM‑powered and agentic systems, including RAG and GraphRAG, hybrid retrieval, agent frameworks (for example LangGraph, LlamaIndex, MCP), context engineering and agent evaluation.

• Deep knowledge of AI infrastructure: vector and graph databases (for example Neo4j, Neptune), embedding and retrieval pipelines, model serving, cloud data platforms (for example Databricks, Snowflake, AWS), and their scale, latency and cost tradeoffs.

• Experience defining semantic layer and metrics strategy so that business definitions stay consistent across BI and AI consumers.

• Experience designing data and knowledge governance, including lineage, provenance, quality, freshness, access control and responsible AI practices.

• Strong programming skills and the ability to write and review production code.

• A pragmatic approach to architecture: you can meet short‑term business needs with flexible solutions while steadily building toward a long‑term vision.

• Excellent communication and the ability to influence without authority. You understand people, process and business needs, and you can speak the business team’s language as fluently as the engineering team’s.

• Experience mentoring and technically guiding teams of data scientists, data professionals and engineers.

• BS in Computer Science, Data Science, Statistics, Information Science or a related field. An MS or PhD is preferred.

Preferred

• Experience with knowledge systems for customer success, customer support or contact‑center environments, such as agent assist, knowledge‑base optimization or self‑service.

• Experience building natural‑language‑to‑SQL or self‑serve data agents over enterprise warehouses.

• Familiarity with semantic web standards (RDF, OWL, SHACL, SPARQL) alongside property graphs (Cypher).

• Experience with LLM evaluation and observability tooling (for example Langfuse, MLflow) and evaluation‑driven development.

• Experience in regulated domains such as finance or tax, where accuracy, provenance and compliance are critical.

• Publications, patents, open‑source contributions or conference talks in knowledge graphs, semantic AI or agentic systems.

Intuit provides a competitive compensation package with a strong pay for performance rewards approach. This position may be eligible for a cash bonus, equity rewards and benefits, in accordance with our applicable plans and programs (see more about our compensation and benefits at Intuit®: Careers | Benefits). Pay offered is based on factors such as job‑related knowledge, skills, experience, and work location. To drive ongoing fair pay for employees, Intuit conducts regular comparisons across categories of ethnicity and gender.

The expected base pay range for this position is:
Mountain View $247,500 - $335,000