Senior AI Agent Architect — Enterprise Leadership

EY; Philadelphia (Philadelphia County); Hybrid; USD 144,000 - 374,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Paid time off

Flexible vacation

Job summary

EY is seeking an experienced AI/ML software engineer to build durable, safe autonomous agents within Challenger. You will design execution loops, tooling, and governance for enterprise-scale workflows, ensuring determinism where needed and safe escalation where necessary.

This role blends applied AI, distributed systems, and product engineering to tackle long-running tasks, real-time failures, and complex model-driven deployments, with a focus on observable behavior and secure, auditable

Qualifications

• Bachelor's degree and relevant experience in software or ML engineering.
• 9-12+ years of experience with production systems and live behavior.
• Hands-on evidence of shipping LLM apps, agents, or complex model-driven workflows.
• Strong Python/TypeScript production skills.

Responsibilities

• Design agent architectures using deterministic steps or multi-agent loops.
• Create connectors and interfaces with clear contracts and safe errors.
• Shape planning, routing, delegation, and retry behavior across workflows.
• Combine instructions, user state, memory, and environment feedback with provenance.
• Implement scoped identities, credentials, and budgets for control.
• Build tests measuring verified task success and safe behavior.
• Use durable state, checkpointing, and safe rollbacks for long-running work.
• Instrument traces and replay for diagnosing failures.
• Provide clear intervention points for user control.
• Publish reusable agent patterns 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

Job description

EY is seeking an experienced AI/ML software engineer to build durable, safe autonomous agents within Challenger. You will design execution loops, tooling, and governance for enterprise-scale workflows, ensuring determinism where needed and safe escalation where necessary.

This role blends applied AI, distributed systems, and product engineering to tackle long-running tasks, real-time failures, and complex model-driven deployments, with a focus on observable behavior and secure, auditable