Director of Agentic AI Engineering

EY; New York (NY); Hybrid; USD 151,000 - 251,000; Full time

Job summary

EY is seeking a senior AI engineer to build agents that move from intent to verified outcomes, engineering execution loops, tools, and controls across complex workflows. You’ll shape behavior, ensure safety, and balance autonomy with user control in a challenging, enterprise setting.

The role sits at the intersection of applied AI, distributed systems, and product engineering, tackling long-running behavior, enterprise integrations, and production failures with measurable outcomes.

Qualifications

• Bachelor’s degree in a relevant field is required.
• 7–9 years of software or applied ML engineering experience.
• Hands-on experience shipping large-language-model apps or agent workflows.
• Strong programming depth in Python, TypeScript, or similar.

Responsibilities

• Choose execution models and design deterministic, single-agent, or coordinated workflows when justified.
• Build dependable tools with clear contracts and safe error handling.
• Engineer agent behavior across planning, routing, and handoffs.
• Create durable context using instructions, memory, and environment feedback.
• Bound agent authority with scoped identities and budgets.
• Evaluate trajectories with tests for task success and recovery.
• Operate long-running execution with durable state and safe retries.
• Make behavior observable with end-to-end traces and replay.
• Protect user control with clear intervention points.
• Build shared capability by partnering across teams and publishing patterns.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Travel up to 50% in hybrid/onsite

Python

TypeScript

Education

Bachelor’s Degree in a relevant field

Tools

None specified

Job description

EY is seeking a senior AI engineer to build agents that move from intent to verified outcomes, engineering execution loops, tools, and controls across complex workflows. You’ll shape behavior, ensure safety, and balance autonomy with user control in a challenging, enterprise setting.

The role sits at the intersection of applied AI, distributed systems, and product engineering, tackling long-running behavior, enterprise integrations, and production failures with measurable outcomes.