Lead AI Agent Engineering Manager

EY; Dallas (TX); Hybride; USD 126 000 - 230 000; Plein temps

Résumé du poste

EY Challenger seeks a senior AI/ML engineer to build long‑running agent systems that execute complex business workflows end‑to‑end. You will design deterministic and delegated agent architectures, implement durable context, and ensure safe, observable operation across large enterprise integrations.

You’ll work in Challenger Core to maintain shared tech and guardrails, collaborating with product, security, and evaluation teams to raise reliability and scale of new services.

Qualifications

• Bachelor’s degree required in a relevant field.
• 7–9 years of software or applied ML engineering with ownership of production systems.
• Hands‑on evidence of shipping LLM apps, agents, or complex model‑driven workflows.
• Strong production services programming skills (Python/TypeScript) and integrations.
• Experience with model APIs, structured outputs, retrieval, memory, and evaluation.

Responsabilités

• Choose the right execution model for agent architectures with deterministic steps or single/coordinated agents when justified by performance.
• Build dependable tools with clear contracts, validated outcomes, and controlled authorization.
• Engineer agent behavior across planning, routing, delegation, retries, and handoffs.
• Create durable context by combining instructions, user state, memory, and environment feedback.
• Bound agent authority with scoped identities, credentials, budgets, and emergency containment.
• Evaluate complete trajectories with tests for verified task success, tool use, and recovery.
• Operate long‑running execution with durable state, checkpointing, and safe retries.
• Make behavior observable with end‑to‑end traces and production evidence.
• Protect user control with clear intervention points for inspection and resume.
• Publish reusable agent patterns and lessons across teams.

Connaissances

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Python

TypeScript

Formation

Bachelor’s Degree in a relevant field

Outils

Python

TypeScript

Description du poste

EY Challenger seeks a senior AI/ML engineer to build long‑running agent systems that execute complex business workflows end‑to‑end. You will design deterministic and delegated agent architectures, implement durable context, and ensure safe, observable operation across large enterprise integrations.

You’ll work in Challenger Core to maintain shared tech and guardrails, collaborating with product, security, and evaluation teams to raise reliability and scale of new services.