Agentic AI Engineer - Manager

EY • Hartford, DC

2d • $125,500 - $261,600 • Hybrid

About The Position

The Agentic AI Engineer will build AI agents that carry meaningful work from user intent to verified outcomes. The role engineers execution loops, tools, context, permissions, evaluations, and runtime controls so agents can operate across complex workflows while remaining understandable, steerable, and safe when systems or assumptions fail. It combines applied AI, distributed systems, and product engineering, with a focus on long-running behavior, enterprise integrations, and production reliability. The engineer determines when deterministic workflows are preferable to autonomy and evaluates whether added complexity provides sufficient operational and user-experience value.

The role is part of EY’s Challenger program, which develops new services and ways of delivering them through AI. Small teams test ideas in real conditions, and solutions demonstrating business value and operational readiness may transition to the business for adoption and scale. Challenger Core develops shared technology, methods, risk and quality guardrails, and reusable tools and practices.

The position requires up to 50% travel and flexibility to work in the office in a hybrid capacity. The salary range depends on location: $150,700–$251,200 in New York City, Boston, Washington DC Metro Areas, Washington State, and Southern California; $157,100–$261,600 in Bay Area California offices; and $125,500–$230,200 in other US office locations, including Sacramento. Individual compensation depends on factors such as education, experience, knowledge, skills, and geography.

Requirements

• Bachelor’s degree in a relevant field of study.
• 7–9 years of experience in software or applied machine-learning engineering, including 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.
• Strong programming capability in Python, TypeScript, or another language used for production services and integrations.
• Experience with model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.
• Practical command of asynchronous work, state, concurrency, idempotency, retries, and failure recovery.
• 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.
• Strong software engineering and distributed-systems judgment, including practical experience building dependable services under failure.
• Ability to reason about agent planning, tools, state, handoffs, and coordination, and to choose a simpler workflow when it performs better.
• Practical knowledge of context, memory, experimentation, and applied AI application patterns.
• Experience measuring complete trajectories and verified outcomes for systems with variable behavior.
• Strong instincts for least privilege, tool boundaries, observability, resilience, recovery, and accountable human intervention.
• Ability to balance quality, latency, cost, and user control and explain technical trade-offs across disciplines.
• Ability to travel up to 50% and flexibility to go into the office in a hybrid capacity.

Nice To Haves

• Experience with durable agent execution, multi-agent systems, or human-agent collaboration.
• Experience integrating agents with permission-sensitive business systems, browsers, or computer-use environments.
• Experience with MCP or comparable standards, enterprise retrieval, knowledge graphs, or context services.
• Experience with sandboxed execution, durable workflow engines, or systems requiring strong evidence and control.
• Practical contributions to agent, evaluation, developer tooling, applied AI, or open-source communities.

Responsibilities

• Design agent architectures using deterministic steps, a single-agent loop, or coordinated agents when measured performance justifies the complexity.
• Create dependable connectors and interfaces with clear contracts, validated outcomes, narrow authorization, and recoverable or escalatable errors.
• Engineer planning, routing, delegation, stopping, retry, and handoff behavior across complete workflows.
• Combine instructions, user state, retrieval, memory, and environment feedback while maintaining relevance, provenance, freshness, and permitted access.
• Implement scoped identities, credentials, budgets, approval points, and emergency containment to bound agent authority.
• Build representative evaluations that measure verified task success, tool use, recovery, human takeover, and prohibited actions across complete trajectories.
• Operate long-running execution using durable state, checkpointing, safe retries, versioned releases, rollback, and graceful degradation.
• Instrument end-to-end traces and replay to diagnose failures, identify patterns, and convert production evidence into improvements.
• Design 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.

Benefits

• Medical and dental coverage.
• Pension and 401(k) plans.
• Flexible vacation policy.
• Paid holidays.
• Winter and summer breaks.
• Personal and family care time off.
• Other leaves of absence to support physical, financial, and emotional well-being.

What This Job Offers

• Job Type: Full-time
• Career Level: Manager