AI Agent Engineering Leader

EY; Woodbridge Township (NJ); Hybrid; USD 125,000 - 230,000; Full time

Job summary

EY is redefining how AI-powered agents operate in enterprise workflows. We are building durable, safe, and observable agent systems that integrate with enterprise tools and governance.

Join a challenging team that blends applied AI, distributed systems, and product engineering to deliver reliable automation at scale. The role requires deep technical execution, collaboration across functions, and travel up to 50% to support hybrid work across US offices.

Qualifications

• Bachelor’s degree in a relevant field.
• 7-9 years of software or applied ML engineering experience with ownership of production systems and live behavior.
• 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.
• Applied AI patterns: model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Distributed execution: asynchronous work, state, concurrency, retries, and failure recovery.
• Identity and controls: access boundaries and scoped authority for applications or automated workloads.
• Production learning: improving live systems via traces, metrics, logs, incident analysis, and durable remediation.
• Travel and On-site requirements: up to 50% travel and hybrid office.

Responsibilities

• Choose the right execution model for agent architectures and measured performance.
• Build dependable tools with clear contracts, validated outcomes, and controlled errors.
• Engineer agent behavior across planning, routing, delegation, stopping, retries, and handoffs.
• Create durable context 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 control.
• Operate long-running execution with durable state, checkpointing, and safe retries.
• Make behavior observable through end-to-end tracing and replay for failure diagnosis.
• Protect user control with clear intervention points to inspect, interrupt, and resume work.
• Build shared capability by partnering across teams and publishing reusable patterns.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Education

Bachelor’s Degree in a relevant field

Job description

EY is redefining how AI-powered agents operate in enterprise workflows. We are building durable, safe, and observable agent systems that integrate with enterprise tools and governance.

Join a challenging team that blends applied AI, distributed systems, and product engineering to deliver reliable automation at scale. The role requires deep technical execution, collaboration across functions, and travel up to 50% to support hybrid work across US offices.