Lead AI Agent Engineer | Hybrid, Growth & Impact

EY; Madison (WI); Hybrid; USD 126,000 - 262,000; Full time

Job summary

EY invites you to join a pioneering Challenger program that builds AI agents capable of operating across long-running, real enterprise workflows. You will design deterministic execution models, create dependable tooling, and ensure safe, observable agent behavior with strong access controls.

The role sits at the intersection of applied AI, distributed systems, and product engineering, tackling big engineering challenges, production failures, and rigor in evaluation.

Qualifications

• Bachelor’s Degree in a relevant field.
• 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.
• Practical command of 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 flexibility to go into the office in a hybrid capacity.

Responsibilities

• Choose the right execution model and design agent architectures with deterministic steps, single-agent loops, or coordinated agents when justified by performance.
• Build connectors and interfaces with clear contracts, validated outcomes, narrow authorization, and recoverable errors.
• Engineer agent behavior across planning, routing, delegation, stopping, retry, and handoff within complete workflows.
• Create durable context by combining instructions, user state, retrieval, memory, and environment feedback.
• Bound agent authority with scoped identities, credentials, budgets, approval points, and emergency containment.
• Evaluate complete trajectories with tests measuring verified task success, tool use, recovery, human takeover, and prohibited actions.
• Operate long-running execution with durable state, checkpointing, safe retries, versioned releases, rollback, and graceful degradation.
• Make behavior observable via end-to-end traces and replay to diagnose failures and derive improvements.
• Protect user control with clear intervention points for inspection, interruption, redirection, and safe resumption.
• Build shared capability by partnering across teams and publishing 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

Tools

Python

TypeScript

Job description

EY invites you to join a pioneering Challenger program that builds AI agents capable of operating across long-running, real enterprise workflows. You will design deterministic execution models, create dependable tooling, and ensure safe, observable agent behavior with strong access controls.

The role sits at the intersection of applied AI, distributed systems, and product engineering, tackling big engineering challenges, production failures, and rigor in evaluation.