Senior AI Agent Architect - Production Systems Lead

EY; Miami (FL); Remote; USD 144,000 - 329,000; Full time

Job summary

EY seeks an experienced AI/ML systems engineer to build durable, steerable agents at Challenger, the firm’s program for next-generation services. You’ll help shape execution loops, tools, context, permissions, evaluations, and runtime controls for agents operating across complex workflows in a safe, understandable way.

This role sits at the intersection of applied AI, distributed systems, and product engineering, with responsibilities spanning long-running behavior, enterprise integrations, and

Qualifications

• Production engineering and distributed-systems judgment.
• Hands-on evidence of shipping large-language-model applications, agents, or complex model-driven workflows used for real work.
• Ownership of production systems and their live behavior.
• Experience with model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Experience implementing access boundaries and scoped authority for applications or automated workloads.
• Travel and On-site requirements: This role requires up to 50% travel and flexibility to go into the office in a hybrid capacity.

Responsibilities

• Design agent architectures that use deterministic steps, a single-agent loop, or coordinated agents only when justified by performance.
• Create connectors and interfaces with clear contracts, validated outcomes, restricted authorization, and recoverable errors.
• Shape planning, routing, delegation, stopping, retry, and handoff behavior across workflows.
• Combine instructions, user state, retrieval, memory, and environment feedback while preserving relevance and provenance.
• Implement scoped identities, credentials, budgets, approval points, and emergency containment for agents.
• Build representative tests that measure verified task success, tool use, recovery, human takeover, and prohibited actions.
• Use durable state, checkpointing, safe retries, versioned releases, rollback, and graceful degradation for long-running work.
• Instrument end-to-end traces and replay to diagnose failures and improve system performance.
• Design clear intervention points so people can inspect, interrupt, redirect, and resume agent work.
• Publish reusable agent patterns and operational lessons across teams.

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 seeks an experienced AI/ML systems engineer to build durable, steerable agents at Challenger, the firm’s program for next-generation services. You’ll help shape execution loops, tools, context, permissions, evaluations, and runtime controls for agents operating across complex workflows in a safe, understandable way.

This role sits at the intersection of applied AI, distributed systems, and product engineering, with responsibilities spanning long-running behavior, enterprise integrations, and