SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
ServiceNow is seeking a Staff Software Engineer (IC4) to design, build, and operate agentic AI capabilities within HR Service Delivery. This role focuses on building AI-native systems—not traditional full-stack engineering—where behavior is model-driven and probabilistic rather than deterministic.
The engineer will own AI design decisions across the HR domain, spanning the entire employee lifecycle: guided service selection and intake, natural-language case creation, conversational case status updates, payroll and benefits inquiry resolution, case triage and routing, eligibility determination, and agent-driven execution of onboarding, transfer, and offboarding events.
Key responsibilities include:
**AI-Native Capability Design**: Build agentic experiences—intent interpretation, multi-step reasoning, tool invocation, and autonomous action—integrated with data models, APIs, and production channels. Design AI-driven workflows by decomposing HR processes into executable steps and decision points, ensuring human checkpoints for changes affecting pay, employment status, or restricted records.
**Instruction Engineering**: Author and maintain system instructions, role definitions, tool descriptions, guardrails, and escalation paths as versioned engineering artifacts under code review and regression coverage. Treat these as public API surfaces for customer configuration and extension.
**Evaluation & Testing**: Design and operate evaluation frameworks for non-deterministic behavior—golden datasets, multi-turn conversation suites, model-as-judge scoring, CI gates, and drift detection. Build HR-specific failure detection (access-boundary violations, PII leakage, jurisdictional correctness) and maintain evaluation across customer configurations.
**Conversational Experience Design**: Build context-aware experiences across channels (portals, chat, workplace messaging, voice) that hand off cleanly between automated and live agents, accounting for latency, speech recognition, and confirmation requirements.
**AI Agent Direction**: Convert requirements into testable specifications with explicit scope, constraints, and acceptance criteria. Supervise multiple workstreams and review AI-generated output for correctness, spec adherence, security, and maintainability.
**Production Quality & Safety**: Monitor conversation quality, hallucination rates, tool-selection errors, and unsafe actions. Defend against prompt injection and data leakage. Maintain observability and rollback mechanisms while protecting restricted HR content. Lead root-cause analysis on agentic behavior deviations.
**Full-Stack Delivery**: Build applications, APIs, data models, and integrations across HCM, payroll, benefits, identity, and knowledge systems with production-grade CI/CD, observability, and upgrade-safe extensibility.
**Cross-Functional Collaboration**: Partner with product, design, conversation design, HR domain, and compliance teams. Mentor IC1–IC3 engineers and raise team practices around instruction authoring, evaluation, and accountable AI use.
**Requirements**
Required:
- 9+ years software engineering experience (backend, frontend, or full stack)
- Strong JavaScript/Node.js, React, and API integration skills
- Automated testing (unit + integration) and CI/CD pipeline experience
- Solid understanding of data modeling and query optimization
- Hands-on experience with AI/GenAI or ML-driven features (LLM prompting, NLU, classification models)
- Hands-on experience with LLM-integrated features: prompt design, context injection, output tuning, guardrails
- Experience with NLU/intent classification or conversational AI systems
- Familiarity with ML-driven automation (classification, clustering, recommendation systems)
- Production AI integration experience: LLM APIs, retrieval-grounded features, agent orchestration, tool/function calling, structured output enforcement
- Applied machine learning literacy: understanding of evaluation, embeddings, probabilistic output, and failure modes of modern models
- Accountable use of AI coding agents with evidence of precise specification, critical review, and verification
- Hands-on CI/CD, containerized workloads, and observability experience; direct on-call and incident-command experience
- Demonstrated mentorship of less-experienced engineers and code review excellence
- Bachelor's degree in computer science, software engineering, or related technical field (or equivalent practical experience)
Preferred:
- HR domain depth: case management, employee lifecycle, payroll, benefits, leave, absence at depth sufficient to challenge requirements
- HCM and downstream integration experience
- Extensible product engineering: customer-configurable capability with versioned contracts
- Evaluation and observability tooling: frameworks, prompt management, tracing, transcript analysis at scale
- Conversational channel breadth: portals, chat, workplace messaging, voice with automated-to-live handoff
- Conversation design partnership experience
- Forward-deployed delivery: building against customer data, integrations, and channels
- ServiceNow Now Platform depth: scoped applications, ACLs, Flow Designer, UI Builder, Automated Test Framework, extension patterns
