AI Agent Architect & Engineering Manager

EY; Baton Rouge (LA); Hybrid; USD 126.000 - 230.000; Vollzeit

Zusammenfassung

EY seeks a seasoned software/AI engineer to build reliable AI agents spanning deterministic and autonomous workflows. You will design execution loops, tools, context, and controls for enterprise-scale integrations, balancing safety, performance, and user control.

Role sits at the intersection of applied AI, distributed systems, and product engineering, focusing on long-running behavior, enterprise integrations, and production failure handling. Up to 50% travel; hybrid office model available.

Qualifikationen

• Bachelor’s degree required; 7–9 years in software or applied ML engineering with ownership of production systems.
• Hands‑on evidence of shipping large‑language-model applications, agents, or complex model‑driven workflows used for real work.
• Strong capability in Python, TypeScript, or another language used for production services and integrations.
• Applied AI patterns: experience with model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Distributed execution: practical command of asynchronous work, state, concurrency, idempotency, retries, and failure recovery.
• Identity and controls: experience implementing access boundaries and scoped authority for applications or automated workloads.
• Production learning: evidence of improving live systems through traces, metrics, logs, incident analysis, and durable remediation.
• Travel and On-site requirements: up to 50% travel with hybrid office capability.

Aufgaben

• Choose the right execution model. Design agent architectures with deterministic steps, a single-agent loop, or coordinated agents only when justified by performance.
• Build dependable tools. Create connectors and interfaces with clear contracts, validated outcomes, narrow authorization, and recoverable errors.
• Engineer agent behavior. Shape planning, routing, delegation, stopping, retry, and handoff across complete workflows.
• Create durable context. Combine instructions, user state, retrieval, memory, and environment feedback while preserving relevance and provenance.
• Bound agent authority. Implement scoped identities, credentials, budgets, approval points, and emergency containment.
• Evaluate complete trajectories. Build tests that measure verified task success, tool use, recovery, human takeover, and prohibited actions.
• Operate long-running execution. Use durable state, checkpointing, safe retries, versioned releases, rollback, and graceful degradation.
• Make behavior observable. Instrument end-to-end traces and replay to diagnose failures and improve production evidence.
• Protect user control. Design clear intervention points for inspection, interruption, redirection, and safe resume of agent work.
• Build shared capability. Partner across teams and publish reusable agent patterns and lessons.

Kenntnisse

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Ausbildung

Bachelor’s Degree in a relevant field

Tools

Python

TypeScript

Jobbeschreibung

EY seeks a seasoned software/AI engineer to build reliable AI agents spanning deterministic and autonomous workflows. You will design execution loops, tools, context, and controls for enterprise-scale integrations, balancing safety, performance, and user control.

Role sits at the intersection of applied AI, distributed systems, and product engineering, focusing on long-running behavior, enterprise integrations, and production failure handling. Up to 50% travel; hybrid office model available.