AI Agent Engineering Manager

EY; Pittsburgh (Allegheny County); Hybrid; USD 126,000 - 262,000; Full time

Benefits offered by this job

Medical and dental coverage

401(k) plans

Paid time off

Job summary

EY is seeking a seasoned software/Applied AI engineer to build and operate long-running AI agent workflows within Challenger. You will design deterministic yet scalable architectures, develop connectors and runtime controls, and push for verifiable outcomes in complex enterprise environments.

The role emphasizes production-grade tooling, cross-functional collaboration, and strong engineering discipline to ensure safe, observable, and controllable agent behavior across diverse systems.

Qualifications

• Bachelor's degree required in a relevant field.
• 7-9 years of software or applied ML engineering experience with production systems live behavior.
• Hands-on evidence of shipping large-language-model applications, agents, or complex model-driven workflows.
• Strong Python/TypeScript production service skills.
• Experience with model APIs, retrieval, tool use, and evaluation of variable behavior.
• Experience with asynchronous work, state, concurrency, 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.
• Up to 50% travel and hybrid office flexibility.

Responsibilities

• Choose the right execution model and design agent architectures that balance determinism and complexity.
• Build dependable tools with clear contracts, validated outcomes, and safe error handling.
• Engineer agent behavior including planning, routing, delegation, and retry logic across workflows.
• Create durable context by combining instructions, user state, retrieval, memory and environment feedback.
• Bound agent authority with scoped identities and budgets.
• Evaluate complete trajectories with tests that measure verified task success and recovery.
• Operate long-running execution using durable state, versioned releases, and safe rollbacks.
• Make behavior observable through end-to-end traces and replay for failure diagnosis.
• Protect user control by enabling interventions and safe resumption of agent work.
• Build shared capability by partnering with product, platform, security, and evaluation 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 is seeking a seasoned software/Applied AI engineer to build and operate long-running AI agent workflows within Challenger. You will design deterministic yet scalable architectures, develop connectors and runtime controls, and push for verifiable outcomes in complex enterprise environments.

The role emphasizes production-grade tooling, cross-functional collaboration, and strong engineering discipline to ensure safe, observable, and controllable agent behavior across diverse systems.