SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 221,200 - 387,100 / annual
ServiceNow seeks a Principal Software Engineer to set technical direction for agentic AI capabilities in the HR Service Delivery (HRSD) domain. This role owns the architecture, standards, and evaluation infrastructure that enable multiple teams to ship safe, intent-driven conversational and agentic experiences for employees, managers, and HR agents.
You will not train foundation models or work on ML research. Instead, you will engineer natural-language-based load-bearing logic (instructions, prompts, context, tool descriptions, guardrails) with the same discipline as traditional code. Because behavior is probabilistic, you will establish correctness through evaluation at scale rather than fixed assertions.
Key ownership areas include:
- AI architecture for the HR domain: agent decomposition and composition, reasoning placement, context assembly and bounding, tool exposure, and autonomy delegation. Own multi-release decisions on model selection, orchestration approach, build-versus-adopt tradeoffs, and cost/latency/quality decisions.
- Autonomy boundary: define which HR actions agents may take autonomously, which require human decision points, and which agents should never attempt. Ensure structural constraints for actions affecting pay, employment status, restricted records, or employee-relations matters.
- Shared instruction and tool description surface: treat as a versioned product contract with upgrade-safe extension points, deprecation paths, and compatibility guarantees for customer configuration and override.
- Evaluation infrastructure: own golden datasets, multi-turn test suites, judge calibration, CI gates, and drift detection. Extend coverage to HR-specific failure classes including access-boundary violations, cross-scope leakage, and jurisdictional/policy-variant correctness.
- Production quality and safety: observability for containment, hallucination rate, tool-selection error, unsafe action, and injection vectors. Design diagnosis that works without exposing restricted HR conversation content.
- AI-assisted engineering standards: convert ambiguous problems into testable specs. Define accountable agent-assisted delivery standards for the domain, including specification standards, review expectations, and verification harnesses.
- Hands-on execution: tackle hard integrations, risky migrations, architectural prototypes, and incidents that block others.
- Cross-functional partnership: collaborate with product, engineering, and design to co-create scalable AI solutions and translate business needs into robust technical designs.
Requirements:
- 10+ years of software engineering with a record of technical direction adopted beyond your immediate team
- Direct, hands-on experience authoring agentic instructions and prompts, designing autonomous workflows, and building evaluation that verifies them
- Production experience with LLM APIs, retrieval-grounded features, agent orchestration, tool and function calling, and structured output enforcement—including at least one model or orchestration migration carried through production
- Entitlement-aware data handling: per-user access enforcement in retrieval and tool layers, scope separation between roles, and handling of restricted records under audit
- Evaluation experience used by engineers other than yourself: dataset curation, judge calibration, CI gating, drift detection
- Strong command of system design, APIs, data modeling, and testing across front-end, server-side, and relational data work with high quality mindset
- Effective, accountable use of AI coding assistants and agents
- On-call and incident-command experience on customer-facing systems, including ownership of systemic fixes that followed
- Experience with Java, JavaScript/TypeScript, React, and demonstrated ability to quickly learn new tools and frameworks
- Bachelor's degree in CS, software engineering, or related technical field, or equivalent practical experience
Preferred:
- HR domain depth: case management, employee journey and lifecycle, or payroll/benefits/leave/absence sufficient to set requirements
- Integration with core HR, payroll, or benefits systems of record, including reconciliation and eventual-consistency patterns
- Contribution in a Forward deployment model to champion customer adoption
