Senior AI Agent Architect

EY; Cleveland (OH); Hybrid; USD 144,000 - 329,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Generous paid time off

Flexible vacation policy

Job summary

EY is seeking a Senior AI/ML engineer to build autonomous agents for enterprise workflows. You will design deterministic and flexible agent architectures, create dependable tooling and safety controls, and collaborate across product, security, and evaluation teams.

You will work in a distributed, high-availability environment, integrating model APIs, memory, and retrieval systems while ensuring observable, auditable behavior and safe user interruption points.

Qualifications

• Production engineering: building reliable distributed systems for live operation.
• Agent architecture: plan, tools, state, handoffs, coordination considerations.
• AI application patterns: model APIs, structured outputs, context, retrieval, memory, tool use.
• Evaluation discipline: measure complete trajectories and verified outcomes in variable systems.
• Security and operability: least privilege, boundaries, observability, resilience, recovery.
• Product judgment: balance quality, latency, cost, and user control; explain trade-offs clearly.
• Programming depth: strong capability in Python, TypeScript or production languages.
• Distributed execution: manage asynchronous state, concurrency, retries, and failure recovery.
• Identity and controls: implement access boundaries for apps/workloads.
• Production learning: improve live systems via traces, logs, incidents.
• Travel and On-site: up to 50% travel with hybrid office access.

Responsibilities

• Choose the right execution model for deterministic vs autonomous workflows.
• Build dependable tools with clear contracts and safe error handling.
• Engineer agent behavior across planning, routing, delegation, stopping, retry and handoff.
• Create durable context from instructions, user state, retrieval and memory.
• Bound agent authority with scoped identities, budgets, approvals, and containment.
• Evaluate complete trajectories with tests for verified task success and recovery.
• Operate long-running execution with durable state, checkpointing, and rollback.
• Make behavior observable with end-to-end traces and replay for improvements.
• Protect user control with clear intervention points for inspection and resume.
• Build shared capability by collaborating across product, platform, knowledge, security, and evaluation.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Python

TypeScript

Education

Bachelor’s Degree in a relevant field

Tools

Python

TypeScript

Job description

EY is seeking a Senior AI/ML engineer to build autonomous agents for enterprise workflows. You will design deterministic and flexible agent architectures, create dependable tooling and safety controls, and collaborate across product, security, and evaluation teams.

You will work in a distributed, high-availability environment, integrating model APIs, memory, and retrieval systems while ensuring observable, auditable behavior and safe user interruption points.