Head AI Agent Engineer: Build Safe, Scalable Autonomy

EY; Rogers (AR); Hybrid; USD 126,000 - 230,000; Full time

Job summary

EY Challenger is seeking an experienced engineer to build long-running AI agents that operate across complex enterprise workflows. You will design deterministic agent architectures, durable toolchains, and safe execution loops while ensuring observability and strong access controls.

The role blends applied AI, distributed systems, and product engineering, focusing on real-world production challenges, continuous improvement, and safe autonomy. Hybrid work and up-to 50% travel are expected.

Qualifications

• Bachelor’s degree in a relevant field is required.
• 7-9 years of software or applied ML engineering with ownership of production systems.
• Hands-on evidence of shipping large-language-model apps, agents, or complex model-driven workflows.
• Strong Python/TypeScript production services experience.
• 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.
• Travel up to 50% and hybrid office presence.

Responsibilities

• Choose the right execution model and architect agent systems with clear contracts and safe operation.
• Build connectors and interfaces with validated outcomes and narrow authorization.
• Engineer agent behavior across planning, routing, delegation, and handoffs.
• Create durable context with instructions, user state, retrieval, memory and environment feedback.
• Bind agent authority with scoped identities, credentials, budgets and approvals.
• Evaluate complete trajectories with tests for verified task success and safe tool use.
• Operate long-running execution using durable state, versioned releases, and safe retries.
• Make behavior observable with end-to-end traces and replay for debugging.
• Protect user control with clear intervention points to inspect, redirect, and resume work.
• Build shared capability by partnering across product, platform, and security teams.

Skills

Python/TypeScript

LLM agents

Distributed execution

Observability

Identity controls

Travel 50%

Education

Bachelor’s Degree in a relevant field of study

Job description

EY Challenger is seeking an experienced engineer to build long-running AI agents that operate across complex enterprise workflows. You will design deterministic agent architectures, durable toolchains, and safe execution loops while ensuring observability and strong access controls.

The role blends applied AI, distributed systems, and product engineering, focusing on real-world production challenges, continuous improvement, and safe autonomy. Hybrid work and up-to 50% travel are expected.