Senior AI Engineer, Agentic Systems & Runtime Architecture

About the Role

We’re looking for a hands‑on Senior AI Engineer to lead the design, build, and operation of production agentic AI systems—including multi‑agent research assistants that deliver cited, grounded answers via conversational experiences and programmatic APIs.

• Collaborate with business and technical stakeholders to translate real‑world research and workflow needs into AI‑powered solutions that are measurable, reliable, and safe in production.
• Architect and build multi‑agent workflows (planner/supervisor + specialist agents) with explicit state management and routing, and interoperability via emerging agent protocols (MCP for tool integration, A2A for agent‑to‑agent delegation).
• Design and continuously improve retrieval architectures for research assistants (hybrid retrieval + reranking), including advanced strategies such as contextual retrieval and embeddings.
• Establish and operationalize Agent Ops‑style evaluation gates: treat the agent as a versioned artifact, run statistical evaluation suites, and use staged rollout approaches to manage risk.
• Implement agentic security controls for systems that ingest external content and use tools/APIs, defending against prompt injection and unsafe tool execution.
• Build production‑grade observability across multi‑step agent executions (traces, metrics, logs), define SLIs/SLOs for reliability and performance, and use telemetry to debug and improve probabilistic runtime behavior.
• Own reliability outcomes: performance and cost trade‑offs, failure isolation, and incident response for AI‑driven components.
• Partner effectively with platform, security, and governance functions—ensuring enterprise standards are met while runtime architecture accountability stays with the team operating the production AI behavior.

• Proven experience designing and building LLM‑powered applications in production, including prompt/tool orchestration and grounded response patterns.
• Hands‑on experience implementing multi‑agent orchestration (planner/supervisor patterns, tool chaining, state management, conditional routing).
• Strong understanding of advanced retrieval for RAG: hybrid retrieval, rank fusion concepts, and reranking; bonus for contextual retrieval/embeddings.
• Demonstrated ability to build evaluation systems for non‑deterministic AI/agent behavior (rubrics, metrics, regression suites, release gates).
• Experience with Agent Ops/LLMOps practices, staged rollout models, and continuous monitoring for quality, drift, safety, and cost‑per‑task.
• Strong security mindset for LLM applications: prompt injection awareness, defense‑in‑depth patterns, and HITL where appropriate.
• Proficiency in Python and modern AI engineering frameworks commonly used for agentic systems.
• Experience designing and managing agent memory systems (working, long‑term, episodic) and scalable prompt architectures.
• Experience building production telemetry and diagnosing distributed workflows using tracing, metrics, logs (Open Telemetry‑style concepts are a plus).
• Bonus: familiarity with Databricks, Azure Foundry, or other cloud AI platform patterns; experience in regulated or audit‑minded environments.

• Healthcare, dental, vision, and life insurance plans
• 401(k) savings plan with generous company matching (up to 6%)
• Voya Retirement Plan – employer‑paid cash balance retirement plan (4%)
• Tuition reimbursement up to $5,250/year
• Paid time off: 20 days paid time off, nine paid company holidays, and a flexible Diversity Celebration Day
• Paid volunteer time – 40 hours per calendar year

Voya Financial is an equal‑opportunity employer. Voya Financial provides equal opportunity to qualified individuals regardless of race, color, sex, national origin, citizenship status, religion, age, disability, veteran status, creed, marital status, sexual orientation, gender identity, genetic information, or any other status protected by state or local law. Voya is committed to the inclusion of all qualified individuals and will provide reasonable accommodations to persons with disabilities as required.