Senior Manager - Agentic AI Engineer (Enterprise)

EY; Hoboken (NJ); Remote; USD 144,000 - 359,000; Full time

Benefits offered by this job

Medical insurance

Dental coverage

Pension/401(k)

Paid time off

Job summary

EY is seeking a seasoned software/AI engineer to build long-running, deterministic and autonomous agent workflows, integrating tools, data, and safety controls. You’ll shape planning, memory, and execution across complex enterprise tasks while maintaining observable, auditable behavior.

Ideal candidates have 9–12+ years of production ML engineering, Python/TS proficiency, and a proven track record shipping large‑language‑model applications.

Qualifications

• Production engineering experience with dependable services.
• Agent architecture and coordination experience.
• AI model APIs, structured outputs, retrieval, and tool use.
• Ability to measure complete trajectories and outcomes.
• Strong security boundaries and observability practices.
• Judgment balancing quality, latency, cost and user control.
• Willingness to travel up to 50% and work in hybrid settings.

Responsibilities

• Choose execution models and architect deterministic or multi-agent flows.
• Build dependable connectors and interfaces with clear contracts.
• Engineer agent behavior across planning, routing and handoffs.
• Create durable context with memory, state and environment feedback.
• Bound agent authority with scoped identities and budgets.
• Evaluate trajectories with tests for verified outcomes.
• Operate long-running execution with durable state and retries.
• Make behavior observable with end-to-end tracing and replay.
• Protect user control with clear intervention points.
• Build shared capability with cross-team collaboration.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Travel and on-site

Education

Bachelor’s degree

Job description

EY is seeking a seasoned software/AI engineer to build long-running, deterministic and autonomous agent workflows, integrating tools, data, and safety controls. You’ll shape planning, memory, and execution across complex enterprise tasks while maintaining observable, auditable behavior.

Ideal candidates have 9–12+ years of production ML engineering, Python/TS proficiency, and a proven track record shipping large‑language‑model applications.