AI Agent Architect Manager

EY; New Brunswick (NJ); Remote; USD 126,000 - 230,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k) plans

Flexible vacation policy

Generous paid time off

Job summary

EY invites you to join Challenger, a new EY program focused on building the firm’s next generation of services. It centers on creating AI-enabled capabilities that move from intent to verified outcomes, engineering the execution loops, tools, context, and controls for safe operation across complex workflows.

This role sits where applied AI, distributed systems, and product engineering meet, addressing long-running behavior, enterprise integrations, and difficult production failures while

Qualifications

• Bachelor’s degree in a relevant field required.
• 7–9 years of software or applied ML engineering experience with production systems ownership.
• Hands-on evidence of shipping large-language-model apps, agents, or complex model-driven workflows.
• Strong capability in Python, TypeScript, or production languages.
• Experience with model APIs, structured outputs, retrieval, and evaluation of variable behavior.
• Practical command of asynchronous work, state, concurrency, retries and failure recovery.
• Experience implementing access boundaries and scoped authority.
• Proven ability to improve live systems through traces, metrics, and incident analysis.

Responsibilities

• Choose the right execution model; design agent architectures with deterministic steps or single-agent loops when justified.
• Build dependable tools with clear contracts, validated outcomes, and controlled errors.
• Engineer agent behavior across planning, routing, delegation, stopping, retry, and handoff.
• 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 and recovery.
• Operate long-running execution using durable state, checkpointing, and graceful degradation.
• Make behavior observable with end-to-end traces and replay for failure analysis.
• Protect user control with intervention points to inspect, interrupt, and resume agent 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

Distributed execution

Travel and onsite awareness

Education

Bachelor’s Degree in a relevant field of study

Job description

EY invites you to join Challenger, a new EY program focused on building the firm’s next generation of services. It centers on creating AI-enabled capabilities that move from intent to verified outcomes, engineering the execution loops, tools, context, and controls for safe operation across complex workflows.

This role sits where applied AI, distributed systems, and product engineering meet, addressing long-running behavior, enterprise integrations, and difficult production failures while