Senior AI Agent Architect & Leader

EY; McLean (VA); Híbrido; USD 144 000 - 374 000; Tempo integral

Resumo da oferta

EY is seeking an experienced AI/ML engineer to build and operate long-running agent systems that translate intent into verified outcomes. You will shape execution loops, tools, context, and governance for enterprise-scale workflows, balancing autonomy with safety and reliability.

This Challenger Core initiative focuses on reusable patterns, enterprise integration, and durable, observable agent behavior across complex business processes.

Qualificações

• Bachelor’s Degree in a relevant field of study.
• 9-12+ years of relevant experience.
• Strong record in software or applied machine-learning engineering, with ownership of production systems and their live behavior.
• Hands‑on evidence of shipping large‑language‑model applications, agents, or complex model‑driven workflows used for real work.
• Programming depth in Python, TypeScript, or production services languages.
• Applied AI patterns: model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Distributed execution: asynchronous work, state, concurrency, idempotency, retries, and failure recovery.
• Identity and controls: access boundaries and scoped authority for applications or automated workloads.
• Production learning: traces, metrics, logs, incident analysis, durable remediation.
• Travel and On‑site requirements: up to 50% travel with hybrid office access.

Responsabilidades

• Choose the right execution model for agent architectures with deterministic steps or single-agent loops.
• Build dependable tools with clear contracts, validated outcomes, narrow authorization, and recoverable errors.
• Engineer agent behavior across planning, routing, delegation, stopping, retry, and handoff in complete workflows.
• Create durable context by combining instructions, user state, retrieval, 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, recovery, and human takeover.
• Operate long-running executions with durable state, checkpointing, and safe retries.
• Make behavior observable via end-to-end tracing and replay for failure diagnosis and improvements.
• Protect user control by enabling interventions and safe resumption of work.
• Build shared capability by publishing reusable agent patterns across teams.

Conhecimentos

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Formação académica

Bachelor's degree

Ferramentas

Python

TypeScript

Descrição da oferta de emprego

EY is seeking an experienced AI/ML engineer to build and operate long-running agent systems that translate intent into verified outcomes. You will shape execution loops, tools, context, and governance for enterprise-scale workflows, balancing autonomy with safety and reliability.

This Challenger Core initiative focuses on reusable patterns, enterprise integration, and durable, observable agent behavior across complex business processes.