Senior Software Engineer, PDX

Overview

ARP evaluates whether internal platforms are “agentic-ready” for end-to-end AI agent development. Its evaluation engine normalizes top use cases, spawns agents in virtualized environments, executes their plans, automatically files issues for friction points (such as missing docs or APIs), and re-runs checks on every CI/CD deploy to prevent regressions. This role sits on the Core Platform Framework team, which builds the evaluation platform and seeks research-minded engineers focused on agent orchestration and LLM tooling, distinct from the Operations/Adoption team.

Responsibilities

• Core platform architecture: build and evolve the virtualization/harness layer, the agent plan-then-execute engine, and the friction detection and auto-ticketing pipeline.
• Model orchestration and cost efficiency: implement dynamic, step-level orchestration, replacing single static models, that routes tasks to cost-effective models (open-source and Claude), tracking cost and performance per step.
• Telemetry and auditability: build scalable logging, cost and telemetry systems so every agent run is fully auditable and cost-accountable.
• Use-case normalization: contribute to technical standards that make use cases agent-readable across differently documented capability platforms.
• Cross-team collaboration: partner with capability, operations and adjacent platform teams on friction reporting, PRD-to-action pipelines, RAG-backed architecture context and OPA policy validation.
• Roadmap leadership: help deliver the roadmap from foundational tooling (plugins, RBAC, alerting) to automation (auto-fix agents, continuous re-runs) and governance visibility.
• Mentorship and standards: mentor junior engineers and contribute to engineering standards through design reviews, architecture documentation and hands-on contributions.

Qualifications

• 7+ years of software engineering experience, focused on distributed systems or developer platforms.
• Hands-on experience building or operating LLM-agent systems: orchestration loops, tool use, plan-and-execute patterns.
• Strong systems programming background (Python, Java) with virtualization, sandboxing or IaC experience.
• Proficiency in Python, Java, Spring Boot, GraphQL and React.
• Applied AI and prompt design skills for reliable, cost-aware LLM behavior.
• Proven ability to lead projects and influence technical direction within and across teams.
• Comfort with ambiguity in a research-driven, next-generation engineering environment.

Preferred

• Building or contributing to LLM or agent evaluation and benchmarking frameworks.
• Policy-as-code, RAG pipelines or vector databases for enterprise agent grounding.
• Cost and token optimization, and multi-model routing.
• Experience with internal developer tools (CI/CD, ticketing automation, developer portals).

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.