AI Agent Architect & Engineering Lead

EY; Tucson (AZ); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Flexible vacation policy

Paid time off options

Health and dental coverage

Job summary

EY is seeking a software/AI systems engineer to build long-running agent workflows within Challenger, EY’s program for next‑generation services. You’ll engineer execution loops, tools, context, permissions, and safety across complex workflows, balancing determinism and autonomy.

You will work at the intersection of applied AI, distributed systems, and product engineering, delivering scalable, enterprise-ready agents and handling difficult production failures with observable metrics and

Qualifications

• Bachelor’s Degree in a relevant field.
• 7-9 years of experience in software or applied machine‑learning engineering with ownership of production systems and live behavior.
• Hands‑on evidence of shipping large‑language-model applications, agents, or complex model‑driven workflows used for real work.
• Strong capability in Python, TypeScript, or another language used for production services and integrations.
• Applied AI patterns: model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Distributed execution: asynchronous work, state, concurrency, idempotency, retries, and failure recovery.
• Identity and controls: access boundaries and scoped authority for applications or automated workloads.
• Production learning: traces, metrics, logs, incident analysis, and durable remediation.
• Travel and on-site: up to 50% travel with hybrid office capability.

Responsibilities

• Choose the right execution model for agent architectures and justify complexity.
• Build dependable tools: connectors with clear contracts, validated outcomes, restricted authorization.
• Engineer agent behavior: planning, routing, delegation, stopping, retry, and handoffs.
• Create durable context: combine instructions, user state, retrieval, memory, environment feedback.
• Bound agent authority: scoped identities, credentials, budgets, and approval points.
• Evaluate complete trajectories: tests measuring verified task success, tool use, and recovery.
• Operate long-running execution: durable state, checkpointing, safe retries, versioned releases, rollback.
• Make behavior observable: end-to-end traces and replay for failure analysis.
• Protect user control: intervention points to inspect, interrupt, redirect, resume agent work.
• Build shared capability: publish reusable agent patterns across teams.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Education

Bachelor’s Degree in a relevant field

Tools

Python

TypeScript

Job description

EY is seeking a software/AI systems engineer to build long-running agent workflows within Challenger, EY’s program for next‑generation services. You’ll engineer execution loops, tools, context, permissions, and safety across complex workflows, balancing determinism and autonomy.

You will work at the intersection of applied AI, distributed systems, and product engineering, delivering scalable, enterprise-ready agents and handling difficult production failures with observable metrics and