Senior AI Agent Architect - Enterprise Automation Leader

EY; Austin (TX); Hybrid; USD 144,000 - 329,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Flexible vacation policy

Paid holidays

Job summary

EY in the US is seeking an experienced software/AI engineer to build long-running AI agents that operate across complex workflows, with a focus on deterministic execution, tool integration, and safe autonomy. You will shape planning, memory, and context, and deliver reusable agent patterns across teams.

The role emphasizes production-grade systems, real-world enterprise deployments, and strong emphasis on security, observability, and controlled autonomy.

Qualifications

• 9-12+ years of software or applied ML engineering experience.
• A strong record in production systems with live behavior ownership.
• Hands-on evidence of shipping large-language-model applications, agents, or complex workflows.

Responsibilities

• Choose the right execution model for deterministic vs. autonomous agents.
• Build connectors and interfaces with clear contracts and validated outcomes.
• Engineer agent behavior across planning, routing, and handoffs.
• Create durable context from instructions, user state, and memory.
• Bound agent authority with scoped identities and budgets.
• Evaluate trajectories with tests for verified outcomes and recovery.
• Operate long-running execution with durable state and safe retries.
• Make behavior observable with traces and replay for failures.
• Protect user control with intervention points to inspect and resume work.
• Build shared capability with cross-team collaboration and reusable patterns.

Skills

Python

TypeScript

Production systems

LLM apps

Agent delivery

Asynchronous programming

Security and access controls

System observability

Education

Bachelor’s Degree

Tools

MCP standards

Knowledge graphs

Context services

Enterprise retrieval

Job description

EY in the US is seeking an experienced software/AI engineer to build long-running AI agents that operate across complex workflows, with a focus on deterministic execution, tool integration, and safe autonomy. You will shape planning, memory, and context, and deliver reusable agent patterns across teams.

The role emphasizes production-grade systems, real-world enterprise deployments, and strong emphasis on security, observability, and controlled autonomy.