Agentic AI Engineer - Senior Manager
Ernst and Young1 day ago
Base Salary
$144k - $374k/yr
Responsibilities
- Design deterministic, single-agent, or coordinated-agent execution architectures based on measured performance and complexity trade-offs.
- Build dependable connectors and interfaces with validated outcomes, narrow authorization, recovery-friendly errors, and enterprise integrations.
- Engineer planning, routing, delegation, stopping, retry, handoff, durable context, retrieval, memory, and environment-feedback behavior.
- Implement scoped identities, credentials, budgets, approval points, emergency containment, and other controls that bound agent authority.
- Build trajectory-level evaluations measuring verified task success, tool use, recovery, human takeover, and prohibited actions.
- Operate long-running executions with durable state, checkpointing, safe retries, versioned releases, rollback, and graceful degradation.
- Instrument end-to-end traces and replay, diagnose production failures, and improve systems using operational evidence.
- Create intervention points that let people inspect, interrupt, redirect, and safely resume agent work.
- Partner with product, platform, knowledge, security, and evaluation teams and publish reusable agent patterns and operational lessons.
Requirements
- Bachelor’s degree in a relevant field of study.
- 9–12+ years of relevant experience in software or applied machine-learning engineering and production-system ownership.
- Hands-on experience shipping large-language-model applications, agents, or complex model-driven workflows used for real work.
- Strong programming capability in Python, TypeScript, or another language used for production services and integrations.
- Practical knowledge of model APIs, structured outputs, retrieval, tool use, context, memory, and evaluation of variable behavior.
- Experience with asynchronous work, state, concurrency, idempotency, retries, and failure recovery in distributed execution.
- 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.
- Preferred experience with durable agent execution, multi-agent systems, human-agent collaboration, permission-sensitive enterprise systems, browsers or computer-use environments, MCP or comparable standards, enterprise retrieval, knowledge graphs, context services, sandboxed execution, durable workflow engines, and open-source or ecosystem contributions.
Benefits
- Base salary ranges from $144,000 to $374,000 depending on office region.
- Medical and dental coverage, pension and 401(k) plans, and paid time off options.
- Flexible vacation policy plus EY-paid holidays, winter and summer breaks, personal/family care, and other leave options.
- Hybrid office flexibility is required, with up to 50% travel.
- Applications are accepted on an ongoing basis, with applicants asked to limit themselves to two applications within six months.
Tech Stack
Categories
About Ernst and Young
Ernst & Young (EY) provides audit/assurance, tax, consulting, strategy and transactions services to enterprises, financial institutions, and public‑sector clients. Structured as a global network of partner‑owned member firms, it sells professional services on a fee basis, including a dedicated Financial Services Organization for banking, insurance, and capital markets. Headquartered in London, EY was formed in 1989 from the merger of Ernst & Whinney and Arthur Young, and operates in 150+ countries.