Senior AI Agent Architect & Leader

EY; Detroit (MI); Hybrid; USD 144,000 - 374,000; Full time

Job summary

EY is seeking an experienced AI/ML engineering leader to build agents that execute complex workflows with determinism and safety. You will shape architectures, tools, and runtimes across enterprise integrations within Challenger, EY's next generation services initiative.

In a role blending applied AI, distributed systems, and product engineering, you’ll tackle long-running behavior, production failures, and real-world adoption at scale, with travel up to 50% and a hybrid office model.

Qualifications

• Bachelor’s degree in a relevant field.
• 9-12+ years of relevant experience.
• Strong record in software or applied ML engineering with ownership of production systems.
• Hands-on evidence of shipping large-language-model applications or complex model-driven workflows.
• Proficiency in Python, TypeScript, or equivalent production languages.
• Experience with model APIs, structured outputs, retrieval, tools, and evaluation of variable behavior.
• Experience with asynchronous work, state, concurrency, retries, and failure recovery.
• Experience implementing access boundaries and scoped authority for apps or automated workloads.
• Evidence of improving live systems via traces, metrics, logs, incidents, and remediation.
• Willingness to travel up to 50% and work in a hybrid capacity.

Responsibilities

• Choose execution models and architect AI agents with deterministic steps where justified.
• Build dependable tools with clear contracts, validated outcomes, and robust error handling.
• Engineer agent behavior across planning, routing, delegation, stopping, retry, and handoff.
• Create durable context by combining instructions, user state, memory, and environment feedback.
• Bound agent authority with scoped identities, credentials, budgets, and containment.
• Evaluate complete trajectories with tests for verified outcomes and safe operation.
• Operate long-running execution with durable state, checkpointing, and safe retries.
• Make behavior observable by instrumenting traces and replay for root-cause analysis.
• Protect user control with clear intervention points to inspect and resume work.
• Build shared capability by publishing reusable agent patterns and lessons.

Skills

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Python

TypeScript

Distributed execution

Education

Bachelor’s Degree in a relevant field

Tools

Python

TypeScript

Job description

EY is seeking an experienced AI/ML engineering leader to build agents that execute complex workflows with determinism and safety. You will shape architectures, tools, and runtimes across enterprise integrations within Challenger, EY's next generation services initiative.

In a role blending applied AI, distributed systems, and product engineering, you’ll tackle long-running behavior, production failures, and real-world adoption at scale, with travel up to 50% and a hybrid office model.