Staff Software Engineer - AI Foundation

Overview

Intuit's strategy is to be an AI-driven expert platform, delivering world-class, revolutionary experiences for our customers at unprecedented speed and scale. The AI Foundation (AIF) Platform team builds and operates the evaluation infrastructure, ML pipelines, and observability tooling that Intuit's agentic product teams (QBO, TurboTax, and others) rely on to ship AI agents safely and quickly. Come join AIF as a Staff Software Engineer to help build the platform that lets the rest of Intuit bring trustworthy, high-quality AI agents to market fast.

Responsibilities

Design and build backend services and pipelines in Python that power agent evaluation, observability, and quality measurement at Intuit scale

Own and evolve core components of the eval platform — golden datasets, LLM-as-judge pipelines, trajectory and correctness scoring, and regression detection across agent releases

Build and operate agent observability infrastructure using Langfuse (or equivalent OTel-based tracing), ensuring product teams have real-time visibility into agent behavior, latency, and failure modes

Design, author, and maintain ML pipelines using Kubeflow Pipelines (KFP), including DAG authoring, artifact tracking, caching/memoization, and deployment on internal Kubernetes (IKS) infrastructure

Drive end-to-end ownership of initiatives — from design through production launch — partnering closely with product agent teams to understand their evaluation and observability needs

Champion a builder culture: experiment with customers to find the best solutions, take on ambiguous problems, and iterate quickly

Use AI/LLM tooling to accelerate your own engineering workflow, and help shape how the broader platform team adopts AI-native development practices

Design and develop highly scalable, high-performance distributed applications and services; expect roughly 80–95% hands-on development/coding.

Mentor and coach other engineers on software engineering best practices, platform architecture, and AI/agent evaluation concepts

Collaborate cross-functionally with data scientists, product managers, and other engineering teams to define what "quality" means for an agent and how the platform measures and guarantees it

Qualifications

Bachelors of engineering in Computer Science or equivalent practical experience

10+ years of experience building and operating distributed backend systems in production

Strong proficiency in Python; solid grasp of software engineering fundamentals (APIs, data modeling, testing, CI/CD)

Hands-on experience with LLM/agent systems: prompt engineering, embeddings, RAG, LLM-as-judge evaluation, or agent frameworks (e.g., LangGraph)

Experience with ML pipeline orchestration — Kubeflow Pipelines, Argo Workflows, or similar — including pipeline authoring, artifact/versioning, and Kubernetes-based deployment

Familiarity with observability/tracing systems for LLM or distributed applications (Langfuse, OpenTelemetry, or comparable)

Experience with at least one major cloud provider (AWS, GCP, or Azure)

Self-starter who can operate with minimal guidance in a fast-moving, ambiguous AI landscape

Strong problem-solving skills, a track record of shipping, and excellent verbal/written communication

Outstanding cross-functional partnership skills; comfortable working with data scientists and product teams, not just engineers

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.