Lead AI Agent Engineer — Safe, Scalable Automation

EY; Los Angeles (CA); Hybride; USD 126 000 - 262 000; Plein temps

Résumé du poste

EY is hiring for a senior AI/ML platform engineer to build deterministic and autonomous AI agents operating within enterprise workflows. You will design agent architectures, durable context, and secure execution across long-running tasks, integrating with enterprise systems and tools.

The role demands hands-on delivery of large-language-model applications, strong Python/TypeScript skills, and a track record of shipping production-grade AI solutions.

Qualifications

• Bachelor’s degree in a relevant field of study.
• 7–9 years of software or applied ML engineering with ownership of production systems and live behavior.
• Hands-on experience shipping large-language-model applications, agents, or complex model-driven workflows.
• Proficiency in Python, TypeScript, or other production languages.
• Experience with model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Distributed execution: asynchronous work, state, concurrency, retries, and failure recovery.
• Experience implementing access boundaries and scoped authority for apps or automated workloads.
• Production learning: traces, metrics, logs, incident analysis, and durable remediation.
• Willingness to travel up to 50% and work in a hybrid/on-site capacity.

Responsabilités

• Choose the right execution model for agent architectures and determine when to use deterministic steps, single-agent loops, or coordinated agents.
• Build dependable tools: connectors and interfaces with clear contracts and narrow authorization.
• Engineer agent behavior across planning, routing, delegation, stopping, retry, and handoff in workflows.
• Create durable context by combining instructions, user state, retrieval, memory, and environment feedback.
• Bound agent authority with scoped identities, credentials, budgets, approvals, and emergency containment.
• Evaluate complete trajectories with tests for verified tasks, tool use, recovery, human takeover, and safety.
• Operate long-running execution with durable state, checkpointing, and graceful degradation.
• Make behavior observable by instrumenting end-to-end traces and replay for failure analysis.
• Protect user control with clear intervention points for inspection, interruption, and resume.
• Build shared capability by partnering across teams and publishing reusable agent patterns.

Connaissances

Production engineering

Agent architecture

AI application depth

Evaluation discipline

Security and operability

Product judgment

Distributed execution

Identity and controls

Travel flexibility

Formation

Bachelor’s Degree in a relevant field

Outils

Python

TypeScript

Description du poste

EY is hiring for a senior AI/ML platform engineer to build deterministic and autonomous AI agents operating within enterprise workflows. You will design agent architectures, durable context, and secure execution across long-running tasks, integrating with enterprise systems and tools.

The role demands hands-on delivery of large-language-model applications, strong Python/TypeScript skills, and a track record of shipping production-grade AI solutions.