Staff Software Engineer

The Staff Software Engineer (IC4) on AI-Native ITSM designs, builds, ships, and operates capabilities whose core behavior is model-driven rather than explicitly authored—agentic and conversational experiences that interpret an IT operator's or end-user's intent, reason over incident, request, change, and knowledge contexts, invoke tools and workflows, and act on the user's behalf across the incident-to-resolution and request-to-fulfillment lifecycles. An agent operating on incidents and requests touches SLA compliance, incident classification accuracy, knowledge fidelity, and user trust—a confidently wrong diagnosis is not a suggestion, it is a failed resolution. At IC4 the engineer owns AI design decisions across the domain, not within a single feature, and owns the correctness of what ships whether a person or an agent produced it. #### What You Do - Build AI-native capability across the IT service management: Design and ship features built around agentic behavior—intent interpretation, multi-step reasoning, tool invocation, and action on the user's behalf—together with the data models, integrations, and channels that make them usable in production. In AI-Native ITSM this spans guided request categorization and routing, natural-language incident description and classification, conversational incident status and in-flight updates, intelligent assignment and routing, knowledge article recommendation and summarization, and auto-remediation orchestration. - Design AI-driven autonomous workflows: Decompose ITSM processes into the steps and decision points an agent can execute—determining where autonomy is appropriate, where a checkpoint with a person is required, and how exceptions, retries, and hand-back are handled. The design must make that distinction structural rather than advisory. - Author and maintain agentic instructions as engineering artifacts: Write, structure, and version the system instructions, role definitions, tool descriptions, guardrails, and escalation paths that govern agent behavior in the domain—under code review, source control, and regression coverage. Own the shared instruction and tool-description surface that adjacent teams build against. - Build automated evaluation and test non-deterministic behavior: Design and operate the evaluation that makes change safe—golden datasets, multi-turn conversation suites, model-as-judge scoring calibrated to human review, CI gates, and drift detection—plus adversarial, jailbreak, grounding, and tool-selection testing. - Design conversational experiences across channels: Build experiences that hold context across turns, hand off cleanly between automated and live agents, and behave consistently across chat and voice—accounting for what voice imposes: latency budgets, barge-in, speech recognition error, disambiguation, and explicit confirmation before consequential actions. - Specify precisely and direct AI coding agents: Convert requirements into testable specifications with explicit scope, constraints, non-goals, and acceptance criteria; decompose work into agent-sized tasks; supervise several workstreams in parallel; and review agent output for correctness, spec adherence, security, and maintainability. You own the result regardless of what produced it. - Own quality, safety, and reliability in production: Monitor conversation quality, containment, hallucination rate, tool-selection error, and unsafe or unauthorized action. Defend against prompt injection and data leakage across integration surfaces. Maintain reasoning-trace observability and model rollback mechanisms, and feed production failures back into specifications and evaluation sets. Lead root-cause analysis when agentic behavior deviates from intent. - Ground it in solid full-stack delivery: Build the application, APIs, data models, and integrations around these capabilities—front-end experiences for IT operators and end-users, server-side logic, and the connections to knowledge, asset, change, and fulfill