Staff Machine Learning Engineer

Company Overview

Intuit is the global financial technology platform that powers prosperity for the people and communities we serve. With approximately 100 million customers worldwide using products such as TurboTax, Credit Karma, QuickBooks, and Mailchimp, we believe that everyone should have the opportunity to prosper. We never stop working to find new, innovative ways to make that possible.

Job Overview

The Network Intelligence Science team builds the intelligence layer that transforms Intuit's expert workforce from a manually coordinated, reactive system into an intelligent, adaptive network that ensures the right experts with the right skills are available exactly when customers need them. We formulate the entire expert network — more than 50,000 experts serving over 100 million customers — as an optimal control problem: demand forecasting predicts future needs, assignment algorithms match tasks to workers under real-time network dynamics, scheduling optimizes expert shifts against projected demand, and capacity planning drives hiring and training decisions. We're replacing today's disconnected, human-bridged tools with a nested hierarchy of forecasting, assignment, scheduling, and supply-planning engines — unlocking scenario planning and durable efficiencies as the platform scales combined services and sales revenue.

As a Staff Machine Learning Engineer, you'll be a technical leader across the team's initiatives, owning ambiguous, end-to-end problems that span multiple systems. You'll set technical direction, establish engineering standards that others build on, and shape how the team approaches evaluation, data, infrastructure, and production ML quality.

Responsibilities

• Architect and own end-to-end ML/optimization systems spanning data pipelines, training, evaluation, and serving, taking on ambiguous problems with significant technical dependencies.

• Establish technical and engineering standards for models, pipelines, and data systems, including schema validation, data contracts, and production-readiness expectations.

• Design and drive adoption of shared ML infrastructure for experimentation, evaluation, observability, and rollback, improving quality and development velocity across the team.

• Apply rigorous statistical and causal methods to quantify uncertainty in demand, assignment, and scheduling decisions, and to inform product and business tradeoffs.

• Apply operations research, optimization theory, control theory, and reinforcement learning to build and continuously tune the demand, assignment, scheduling, and supply engines that run the expert network in real time.

• Productionize forecasting, optimization, and simulation systems that plan and adjust expert capacity, schedules, and task assignments across real-time and long-horizon time scales, including the serving and feedb