Consultant

Experience : 6 to 9 Years Job Role We are looking for creative problem solvers with a passion for tackling tough customer problems involving data to serve as a Knowledge Enablement Engineer, with responsibility for evaluating, piloting, and then scaling the capability that makes our data findable, trustworthy, and usable — by people and by AI agents. If you're passionate about large initiatives at a scale that helps transform the lives of internal and external stakeholders, this is that kind of work. Intuit's Global Business Solutions Group builds tools and services that help small and mid-sized businesses manage cash flow and grow. Within this mission, our Data Science team is building the knowledge layer between our data and the people and agents who use it: canonical metric definitions, semantics, data dictionaries, and the surfaces that make them discoverable. This role sits at the intersection of semantic modeling and AI enablement. We are looking for a proactive, end-to-end contributor: someone who can evaluate existing capabilities on their merits, stand up a working pilot rather than an assessment, make a clear recommendation, and carry it into adoption. Programs for the coming year involve everything from evaluating existing tools across semantics, context, and knowledge graphs, to piloting the strongest option and determining how our current semantic layer feeds into it, to scaling the result across Responsibilities Evaluation and pilot Evaluate existing tools and platforms across semantics, context, and knowledge graphs, and assess our requirements against them Pilot the strongest option, and determine how our existing semantic layer serves as an input to it Deliver a working pilot together with a clear recommendation Adoption and scale Onboard domains onto the approach we adopt, expanding content coverage as you go Support alignment sessions so that definitions are agreed before they are codified Create playbooks and establish best practices so each domain onboards more easily than the last Build and integration Author the AI rules, skills, and files that make the layer usable by both people and agents Develop tool-agnostic capabilities that serve multiple AI tools rather than a single vendor Integrate through code or configuration depending on the adoption path, and evaluate graph-based approaches as a later component What you'll bring Demonstrated depth building semantic layers, knowledge graphs, retrieval systems, or agent tooling. A proactive, end-to-end approach, and comfort operating with a high degree of autonomy SQL and Python sufficient to work on a data science team; SQL forms part of the content itself Experience building with modern AI tooling; transferable experience matters more to us than any specific vendor Demonstrated ability to build strong partnerships across teams, including outside your own organization Technical education or equivalent work experience How you will contribute Focus strategically. Has autonomy to work collaboratively with the leaders in your space to drive the evaluation and rollout. Makes and defends build-versus-adopt judgments — a well-reasoned recommendation to reuse an existing capability is as valuable to us as a recommendation to build a new one. Deliver. Produces a working pilot rather than an assessment, and sequences the rollout so that each domain onboarded is a durable gain. Uses independent judgment to provide insights, and communicates progress, trade-offs, and risks to stakeholders. Collaborates closely with the hiring manager on review of design and requirements. Preferred qualifications Experience with semantic layers or specifications such as MetricFlow or Open Semantic Interchange Experience with MCP servers, agent orchestration, or retrieval systems Experience driving adoption of a platform capability across multiple teams Required skills SQL and Python sufficient to work on a data science team; SQL forms part of the content itself Experience building with modern AI tooling; transferable experience matters more to us than any specific vendor #J-18808-Ljbffr LatentView Analytics