Senior AI Engineer, Agentic Systems & Runtime Architecture

Together we fight for everyone’s opportunity for a better financial future.

We will do this together — with customers, partners and colleagues. We will fight for others, not against: We will stand up for and champion everyone’s access to opportunities. The status quo is not good enough … we believe every individual and every community deserves access to financial opportunities. We are determined to support both individuals and communities in reaching a better financial future.  We know that reaching this future depends on our actions today.

Like our Purpose Statement, Voya believes in being bold and committed to action.  We are committed to a work environment where the differences that we are born with — and those we acquire throughout our lives — are understood, valued and intentionally pursued. We believe that our employees own our culture and have a responsibility to foster an environment where we all feel comfortable bringing our whole selves to work. Purposefully bringing our differences together to positively influence our culture, serve our clients and enrich our communities is essential to our vision.

Are you ready to join a company with a strong purpose and a winning culture? Start your Voyage – Apply Now

About the RoleWe’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 both conversational experiences and programmatic APIs. You’ll own “runtime architecture” decisions (orchestration/routing, retrieval strategy, model serving patterns, and runtime controls) and help evolve our capabilities toward more sophisticated agentic design: planner/supervisor orchestration, advanced retrieval + reranking, evaluation gates (AgentOps), agentic security, and end-to-end observability.What You’ll Do

• 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) designed for non-deterministic behavior and real operational constraints.
• Design and continuously improve retrieval architectures for research assistants (hybrid retrieval + reranking), including advanced strategies such as contextual retrieval / contextual embeddings to reduce retrieval failures and improve grounding coverage.
• Establish and operationalize AgentOps-style evaluation gates: treat the agent as a versioned artifact (model + prompt + tools + guardrails + eval thresholds), run statistical evaluation suites, and use staged rollout approaches to manage risk while maintaining iteration speed.
• Implement agentic security controls for systems that ingest external content and use tools/APIs, including defenses against prompt injection and unsafe/over-broad 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 tradeoffs (latency/throughput/cost), 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.
• Rapid learner with a hands-on mindset — able to quickly ramp up on emerging AI frameworks and tooling, prototype rigorously, and translate new developments into production-ready implementations with engineering discipline.

What You Bring

• 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, and conditional routing.
• Strong understanding of advanced retrieval for RAG: hybrid retrieval, rank fusion concepts, and reranking, with bonus points for contextual retrieval