Agentic Solutions Architect

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 Conduct agentic platform strategy and architect reference designs and standards. Define, document, and evangelize cross‑platform best practices for cost, performance, design, and integrations. Guide platform selection and build allocation, balancing capability, cost, integration fit, security, and maintainability. Set technical direction and review contractor work on agent building, ensuring quality, security, and adherence to standards. Serve as the technical authority for agentic systems, mentoring engineers and driving alignment with IT, Engineering, Cloud Operations, Security, Product, and field stakeholders. Advance Splunk’s revenue and customer‑success goals by increasing technical sellers’ customer‑facing time and improving the agents behind demonstrations and Field Solutions Apps. Deliver 3 to 5 production agents that streamline technical sellers’ daily workflows, prioritizing use cases that return the most selling time. Perform last‑mile build and integration of agents, wiring up tools, Model Context Protocol (MCP) servers and clients, data sources, and integrations. Translate reference designs into working agentic systems with evaluation and guardrails designed from the start, and define retrieval (RAG) and tool‑integration strategies. Establish comprehensive observability, monitoring, and alerting for agents in production, ensuring deep visibility into agent health, behavior, and performance. Track resource consumption, define and monitor SLOs/SLIs, manage cost‑per‑task economics, and drive model‑routing and efficiency decisions. Define and enforce governance and guardrails to keep agents safe, within budget, and compliant with security and regulatory standards. Maintain a subset of production agents, resolving regressions, keeping them current as platforms and models evolve, and optimizing prompts, tools, topologies, and guardrails. Qualifications 3+ years of software, ML, or platform engineering experience. Track record of technical leadership and influence without direct‑report or people‑management responsibilities. Hands‑on experience designing and building production agentic systems, including multi‑agent orchestration and Model Context Protocol (MCP) integrations. Experience selecting among and building across multiple agent platforms. Strong tool and API integration skills, including designing retrieval (RAG) strategies. Experience building evaluation harnesses and conducting offline/online evaluations, validating agentic systems in simulation before release. Experience implementing guardrails, policy, permission models, and audit trails for autonomous systems. Familiarity with token and cost management across multiple LLM providers. Experience directing and reviewing contractor or peer engineering work through technical review. Hands‑on experience operating agents in production with observability and monitoring (Splunk, Splunk Observability). Experience with Splunk products (Cloud/Enterprise, ITSI, Observability) for telemetry and monitoring. Proficiency in cloud‑native architectures, preferably AWS. Experience in programming/scripting languages such as Python and Bash. Understanding of distributed systems, microservices architecture, and API design. Strategic thinking and ability to translate business objectives into technical roadmaps. Excellent communication skills and ability to present technical concepts to non‑technical stakeholders. Track record of delivering results in fast‑paced, dynamic environments. Data‑driven decision‑making approach with focus on measurable outcomes. Core Values and Mindsets Commitment to Excellence – dedication to high‑quality solutions and continuous improvement. Adaptability / Flexibility – growth mindset and effective response to rapid change. Collaboration – strong team player attitude and communication. Ownership – proactive approach to improvement and accountability. Innovation – passion for creative problem‑solving and technical rigor. Fun – embrace fun, celebrate success, and contribute to a positive culture. #J-18808-Ljbffr Cisco