AI Agent Engineering Manager

EY; Richmond (VA); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Extensive paid time off

Flexible vacation policy

Job summary

EY is building a new Challenger program in AI/ML that focuses on scalable agent-based services. You will design and implement deterministic and multi-agent workflows, integrating tools, context, and safety controls across complex enterprise integrations.

The role emphasizes production engineering, security, observability, and continuous improvement through traces and metrics. Travel up to 50% and hybrid in‑office work are expected in a national scope.

Qualifications

• Bachelor’s degree in a relevant field and 7–9 years building production software or applied ML systems.
• Hands‑on evidence of shipping large‑language-model applications or complex model‑driven workflows.
• Strong capability in Python, TypeScript, or other production languages.
• Experience with model APIs, structured outputs, retrieval, tool use and evaluation of variable behavior.
• Practical command of asynchronous work, state, concurrency, retries and failure recovery.
• Experience implementing access boundaries and scoped authority for automated workloads.
• Evidence of improving live systems through traces, metrics, logs and incident analysis.
• This role requires up to 50% travel with hybrid in-office capability.

Responsibilities

• Choose the right execution model and design agent architectures for deterministic or coordinated workflows.
• Build dependable tools and interfaces with clear contracts and validated outcomes.
• Engineer agent behavior including planning, routing, delegation and retry logic.
• Create durable context by combining instructions, user state and environmental feedback.
• Bound agent authority with scoped identities, credentials and budgets.
• Evaluate complete trajectories with tests for verified task success and recovery.
• Operate long‑running execution with durable state, versioned releases, and graceful degradation.
• Make behavior observable by instrumenting traces and replay of production events.
• Protect user control with clear intervention points to inspect and resume work.
• Build shared capability by collaborating with product, platform, security and evaluation teams.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Travel flexibility

Education

Bachelor’s Degree in a relevant field of study

Job description

EY is building a new Challenger program in AI/ML that focuses on scalable agent-based services. You will design and implement deterministic and multi-agent workflows, integrating tools, context, and safety controls across complex enterprise integrations.

The role emphasizes production engineering, security, observability, and continuous improvement through traces and metrics. Travel up to 50% and hybrid in‑office work are expected in a national scope.