• Drive the technical direction for our AI-driven application-builder architecture • Lead complex system design decisions • Serve as a hands-on technical leader and mentor for the engineers building AI Studio’s app generation engine • Partner closely with product, infra, and design to shape the roadmap • Build scalable, fault-tolerant LLM pipelines for content generation, layout creation, experimentation, and AI-driven user guidance • Work hands-on with technologies like Go, NestJS, Node, PostgreSQL, Firestore, Vector Databases, Cloudflare Workers, Cloudflare KV, and microservices • Design distributed systems that handle high-throughput generative and analytical workloads while ensuring correctness and low latency • Drive improvements in observability using Prometheus/Grafana, OpenTelemetry, and structured logging • Mentor engineers through code reviews, design discussions, and pairing • Participate in reviews, deep dives, and on-call rotations to maintain a culture of accountability and operational excellence

• Design and build AI applications powered by LLMs, RAG, semantic search, and AI agents. • Develop intelligent pipelines for document ingestion, knowledge extraction, and retrieval. • Improve answer quality through prompt engineering, evaluation frameworks, and retrieval optimization. • Build and optimize production AI services using Python and modern AI frameworks. • Work with agentic development tools including Claude Code, Cursor, and AI-assisted coding workflows. • Write clean, maintainable, well-tested code with a strong focus on quality and reliability. • Collaborate closely with product, engineering, and data science teams to rapidly prototype and ship new capabilities. • Evaluate emerging AI models, tools, and techniques to continuously improve the platform.

• Scope Knowledge Engine: ontology, data catalog, schema governance; • Design MCP architectures (Knowledge-Memory, API Bridge, Webhook Agents); • Build Context Engineering Layer (CLAUDE.md, AGENTS.md, harness patterns); • Curate agent skills, prompts, rubrics, and harness configs; • Own Accelerator Solution Map: toolkits, gap analysis, specifications; • Bridge EA and service teams - translate strategy into guidance; • Define SDLC standards and Operating Model artifacts; • Deliver EA leadership artifacts (Maturity Map, Dashboard, Portfolio, Integration Map, AI Scorecard).

Role Description We are seeking a Senior Staff Software Engineer to serve as the technical visionary and architect for our multi-agent harness platform, and writing agents for our products. This is a high-leverage, tier-one leadership opportunity operating at the absolute frontier of Agent research and large-scale backend systems engineering. In this role, you won't just implement agents—you will define the architectural patterns, scalability guardrails, and strategic direction for how intelligent, autonomous agents reason, decide, and secure the modern enterprise. What You Will Do - Architect & Vision: Define the technical roadmap and architecture for Access AI Platform, ensuring high availability, low latency, and deterministic reliability. - System Design: Lead the design of advanced agent orchestration layers, multi-agent communication, and sophisticated context/memory management. - Productionize at Scale: Transition cutting-edge LLM capabilities and MCP frameworks from experimental prototypes into hardened, enterprise-grade pipelines within our identity access infrastructure. - Technical Leadership: Act as a force multiplier across the engineering organization. Define engineering excellence, establish robust test/evaluation frameworks for non-deterministic AI systems, and mentor senior and staff-level engineers. - Cross-Functional Influence: Partner closely with Product, Security, and Executive leadership to align technical investments with long-term business strategy, pioneering new capabilities from ideation to global deployment. Qualifications - Education: Bachelor’s, Master’s, or PhD in Computer Science, Engineering, or a related technical field. - Experience: - 10+ years of professional software engineering experience, with a proven track record of technical leadership at a Staff or Senior Staff level. - 2+ years of hands-on experience in architectural design and production deployment of GenAI technologies, multi-agent systems, LLM orchestration frameworks (e.g., LangChain, AutoGen), or Model Context Protocols (MCP). - Technical Mastery: - Expert-level proficiency in Python and Golang (or Java), with deep expertise in distributed systems, microservices architectures, and high-throughput API design. - Deep understanding of Cloud Platforms (AWS, Azure, GCP) with experience designing or integrating with enterprise Identity and Access Management (IAM) environments and security fabrics. - Execution & Ownership: A strong sense of product ownership. You have a history of taking ambiguous, 0-to-1 AI initiatives and scaling them to 1-to-100 enterprise realities. - Communication: Exceptional communication skills with a demonstrated ability to distill complex AI reasoning and architectural trade-offs into clear, strategic narratives for both engineering teams and executive boardrooms. Requirements - For positions in this location, we offer a base pay of $171,900 - $300,800, plus equity (when applicable), variable/incentive compensation and benefits. - Sales positions generally offer a competitive On Target Earnings (OTE) incentive compensation structure. - Please note that the base pay shown is a guideline, and individual total compensation will vary based on factors such as qualifications, skill level, competencies, and work location. - We also offer health plans, including flexible spending accounts, a 401(k) Plan with company match, ESPP, matching donations, a flexible time away plan and family leave programs. Benefits - Flexible work personas (flexible, remote, or required in office). - Equal Opportunity Employer: All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, national origin, age, disability, gender identity, veteran status, or any other category protected by law. - Accommodations available for candidates requiring assistance during the application process. - Employment is contingent upon ServiceNow obtaining any export license or other approval that may be required by relevant export control authorities.