Senior AI Agent Architect for Enterprise Workflows

EY; Phoenix (AZ); Hybrid; USD 144,000 - 329,000; Full time

Job summary

EY invites exceptional candidates to join Challenger Core, EY's program blending applied AI, distributed systems, and product engineering. You will architect durable AI agents, build tools, and govern workflows across enterprise integrations while balancing safety, control, and performance.

You’ll work inside Challenger Core teams, shaping long-running behavior, observing systems, and delivering scalable, testable AI solutions with strong emphasis on operational readiness and risk management.

Qualifications

• Bachelor’s Degree in a relevant field of study.
• 9-12+ years of relevant experience.
• Strong track record in software or applied machine-learning engineering with ownership of production systems.
• 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.
• Experience with model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Command of asynchronous work, state, concurrency, idempotency, retries, and failure recovery.
• Experience implementing access boundaries and scoped authority for applications or automated workloads.
• Evidence of improving live systems through traces, metrics, logs, incident analysis, and durable remediation.
• Travel and On‑site requirements: up to 50% travel and hybrid office flexibility.

Responsibilities

• Choose the right execution model and design agent architectures with deterministic steps or single-agent loops where justified.
• Build dependable tools with clear contracts, validated outcomes, narrow authorization, and recoverable errors.
• Engineer agent behavior across planning, routing, delegation, stopping, retry, and handoff.
• Create durable context by combining instructions, user state, retrieval, memory, and environment feedback.
• Bound agent authority with scoped identities, credentials, budgets, and emergency containment.
• Evaluate complete trajectories with tests measuring verified task success, tool use, recovery, and human takeover.
• Operate long-running execution with durable state, checkpointing, and graceful degradation.
• Make behavior observable with end-to-end traces and replay for failure diagnosis and improvements.
• Protect user control with intervention points to inspect, interrupt, or resume agent work.
• Build shared capability by partnering across product, platform, security, and evaluation teams.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Education

Bachelor’s Degree in a relevant field of study

Tools

Python

TypeScript

Job description

EY invites exceptional candidates to join Challenger Core, EY's program blending applied AI, distributed systems, and product engineering. You will architect durable AI agents, build tools, and govern workflows across enterprise integrations while balancing safety, control, and performance.

You’ll work inside Challenger Core teams, shaping long-running behavior, observing systems, and delivering scalable, testable AI solutions with strong emphasis on operational readiness and risk management.