About the company
It all started when engineer Fred Luddy wrote code that automated a tedious task for his coworker, Phyllis. She cried tears of joy. That moment inspired Fred to build a company that could do that for everyone—freeing people from busywork so they could focus on meaningful work. Today, ServiceNow is the AI control tower for business reinvention. Our ServiceNow AI platform brings together any AI, any data, and any workflow— helping 85% of the Fortune 500® work smarter, faster, and better. We're building an AI-native culture where technology and talent are unstoppable together. And we're just getting started.
Responsibilities
- Design, build, and deliver scalable, AI-native enterprise applications for industry-specific workflows, data models, and compliance requirements, along with the integrations and channels that make them usable in production.
- Build agentic behavior into those applications: intent interpretation, multi-step reasoning, tool and function invocation, and action on the user's behalf, delivered through conversational experiences across chat (and voice where the use case calls for it) that hold context and hand off cleanly between automated and human agents.
- Design AI-driven autonomous workflows: decompose business processes into the steps and decision points an agent can execute, decide where autonomy is appropriate and where a human checkpoint is required, and define how exceptions, retries, and hand-back to a person are handled.
- Author and maintain agentic instructions (system instructions, role definitions, tool descriptions, guardrails, and escalation rules) as versioned engineering artifacts under review and regression coverage, not configuration text.
- Engineer prompts for reliability rather than demo quality, iterating against measured outcomes: task decomposition, golden examples, structured output schemas, grounding and citation, graceful failure, and token and latency cost.
- Build automated evaluation and test non-deterministic behavior: golden datasets, multi-turn conversation suites, model-as-judge scoring calibrated to human review, CI gates, drift detection, and adversarial, jailbreak, grounding, and tool-selection testing.
- Design software that lets customers configure and extend platform capabilities without sacrificing performance.