AI Agent Engineering Manager

EY; Hoboken (NJ); Hybrid; USD 126,000 - 262,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Paid time off

Job summary

EY’s Challenger program seeks an experienced engineer to build AI agents that run long‑running workflows and enterprise integrations. You will design deterministic execution loops, develop dependable tools, and shape agent behavior while ensuring safety, observability, and controllability across complex production systems.

Travel up to 50% and a hybrid office presence are expected as you work across product, platform, security, and evaluation teams to deliver scalable, auditable AI solutions

Qualifications

• Bachelor’s Degree in a relevant field (required).
• 7–9 years of experience in software or applied machine-learning engineering 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.
• 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.
• This role requires up to 50% travel and hybrid office presence.

Responsibilities

• Choose the right execution model. Design agent architectures that use deterministic steps, a single‑agent loop, or coordinated agents only when measured performance justifies the complexity.
• Build dependable tools. Create connectors and interfaces with clear contracts, validated outcomes, narrow authorization, and errors that help the agent recover or elevate.
• Engineer agent behavior. Shape planning, routing, delegation, stopping, retry, and handoff behavior across complete workflows.
• Create durable context. Combine instructions, user state, retrieval, memory, and environment feedback while preserving relevance, provenance, freshness, and access permissions.
• Bound agent authority. Implement scoped identities, credentials, budgets, approval points, and emergency containment so agents act within explicit limits.
• Evaluate complete trajectories. Build tests that measure verified task success, tool use, recovery, human takeover, and prohibited actions.
• Operate long‑running execution. Use durable state, checkpointing, safe retries, versioned releases, rollback, and graceful degradation.
• Make behavior observable. Instrument end‑to‑end traces and replay to diagnose failures and drive improvements.
• Protect user control. Design clear intervention points for inspection, interruption, and safe resumption.
• Build shared capability. Partner across teams and publish reusable agent patterns and operational lessons.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Education

Bachelor’s Degree in a relevant field

Tools

Python

TypeScript

Job description

EY’s Challenger program seeks an experienced engineer to build AI agents that run long‑running workflows and enterprise integrations. You will design deterministic execution loops, develop dependable tools, and shape agent behavior while ensuring safety, observability, and controllability across complex production systems.

Travel up to 50% and a hybrid office presence are expected as you work across product, platform, security, and evaluation teams to deliver scalable, auditable AI solutions