Agentic Solutions Architect

The application window is expected to close on: 08/04/2026

** Job posting may be removed earlier if the position is filled or if a sufficient number of applications are received** .

** This role can be performed anywhere in the Central and Eastern United States.*
* ** Role*
* ** Summary*
* Splunk is seeking a senior individual contributor to serve as the technical lead for the AI agents that make our technical sellers more productive, setting direction through thought leadership and influence across field teams. The role spans the full agent lifecycle across multiple platforms: setting best practices for cost, performance, design, and integrations; deciding which agents are built where; completing the last-mile build;

maintaining a subset in production; and directing and reviewing a contractor who builds additional agents. You will combine agentic engineering (designing and building agents) with agentic operations (running them reliably, safely, and cost-effectively) as the single technical authority guiding quality from design through production. Your immediate mission is to deliver an initial 3 to 5 agents that streamline technical sellers' daily workflows, freeing them to spend more time customer-facing and advancing Splunk's revenue and customer-success goals.

** Responsibilities*
* ** Agentic Platform Strategy (Architect)*
* ** Reference Design & Standards:
** Advise on the end-to-end design for agentic systems across platforms, contributing inputs to the reference designs, patterns, and standards agents are built against, and informing system-level decisions on how agents reason, integrate, and scale.

** Cross-Platform Best Practices:
** Define, document, and evangelize best practices for cost, performance, design, and integrations across the organization's agent platforms, so teams build consistently and avoid duplicated effort.

** Platform Selection & Build Allocation:
** Guide which agents are built on which platform, balancing capability, cost, integration fit, security, and maintainability, and set the criteria the organization uses to decide.

** Contractor Direction & Review:
** Set technical direction for a contractor building agents, specifying what to build and where, and reviewing their work for quality, security, and adherence to standards. (Technical direction and review, not people management.)

** Technical Thought Leadership & Influence:
** Serve as the recognized technical authority for agentic systems across field teams, contributing to reference designs and standards, mentoring engineers, and driving alignment with IT, Engineering, Cloud Operations, Security, Product, and field stakeholders through influence.

** Strategic Impact:
** Advance Splunk's revenue and customer-success goals by increasing technical sellers' customer-facing time and making the agents behind demonstrations and Field Solutions Apps more capable, reliable, safe, and cost-effective.

** Agent Delivery & Engineering (Build)*
* ** Deliver Seller-Productivity Agents:
** Own delivery of an initial 3 to 5 production agents that streamline technical sellers' daily workflows, prioritizing the use cases that return the most selling time and measurably reduce manual effort.

** Last-Mile Build & Integration:
** Complete the last-mile build of agents, wiring up tools, Model Context Protocol (MCP) servers and clients, data sources, and integrations, and hardening them from prototype to dependable production use.

** Agent Design & Orchestration:
** Translate the reference design into working agentic systems with evaluation and guardrails designed in from the start, and define retrieval (RAG) and tool-integration strategies that keep agents grounded and accurate.

** Agentic Operations (Operate)*
* ** Observability & Monitoring:
** Establish comprehensive logging, monitoring, and alerting for agents in production. Because agents make non-deterministic decisions, ensure deep visibility into agent health, behavior, and performance, and lead root-cause analysis when agents fail.

** Performance & Cost Evaluation:
** Track resource consumption across agentic workloads, including API usage and token limits across LLMs. Define and monitor SLOs/SLIs, manage cost-per-task economics, and drive model-routing and efficiency decisions that keep performance high and spend predictable.

** Governance & Guardrails:
** Define the boundaries that keep agents safe, within budget, and compliant with security and regulatory standards, establishing policy, permissions, audit trails, and human-in-the-loop checkpoints so every agent action is bounded, traceable, and auditable.

** Continuous Optimization & Maintenance:
** Maintain a subset of production agents, resolving regressions and keeping them current as platforms and models evolve, while using telemetry and evals to refine prompts, tools, topologies, and guardrails. Validate changes in simulation before release and automate away manual toil.

** Qualifications*
* ** Technical Skills**  **:*
* 3+ years of software, ML, or platform…