Lead AI Agent Engineering Manager

EY; Buffalo (NY); Hybrid; USD 126,000 - 262,000; Full time

Job summary

EY is seeking engineers to build AI agents enabling deterministic workflows and safe, auditable automation across complex enterprise integrations. You will shape long-running behavior, handle production failures, and decide when autonomy adds value, balancing risk and operational cost.

The role sits within Challenger, EY’s program focused on new AI-enabled services, with opportunities to ship end-to-end model-driven workflows and contribute reusable tools and practices. Hybrid travel up to 50%.

Qualifications

• Bachelor’s degree in a relevant field.
• 7–9 years of software or applied ML engineering with ownership of production systems and live behavior.
• Hands-on evidence of shipping large-language-model applications, agents, or complex model-driven workflows.
• Strong programming in Python, TypeScript, or other production languages.
• Experience with model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Experience with 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 up to 50% and hybrid on-site flexibility.

Responsibilities

• Choose the right execution model for agent architectures.
• Build dependable tools with clear contracts and validated outcomes.
• Engineer agent behavior for 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 and budgets.
• Evaluate complete trajectories with tests for verified outcomes, 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.
• Protect user control with clear intervention points for inspection and safe resumption.
• Build shared capability by partnering across teams and publishing reusable agent patterns.

Skills

Production eng

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Education

Bachelor’s Degree

Tools

MCP

Knowledge graphs

Job description

EY is seeking engineers to build AI agents enabling deterministic workflows and safe, auditable automation across complex enterprise integrations. You will shape long-running behavior, handle production failures, and decide when autonomy adds value, balancing risk and operational cost.

The role sits within Challenger, EY’s program focused on new AI-enabled services, with opportunities to ship end-to-end model-driven workflows and contribute reusable tools and practices. Hybrid travel up to 50%.