SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 166,500 - 291,400 / annual
ServiceNow is seeking a Staff Software Engineer to set technical direction for agentic AI capabilities within the HR Service Delivery (HRSD) domain. This role owns the architecture, standards, and evaluation infrastructure that enable multiple teams to ship conversational and agentic experiences safely—not a single feature set.
You will architect how agents are decomposed and composed, where reasoning happens, how context is assembled and bounded, and how tools are exposed. You'll establish the autonomy boundary as domain policy, deciding which HR actions agents may take autonomously, which require human decision points, and which agents should never attempt. This includes ensuring that actions affecting pay, employment status, restricted records, or employee-relations matters have structural human-in-the-loop controls.
You'll own the shared instruction and tool description surface as a versioned contract with upgrade-safe extension points, deprecation paths, and compatibility guarantees. You'll build evaluation as infrastructure—golden datasets, multi-turn test suites, judge calibration, CI gates, and drift detection—extending coverage to HR-specific failure classes like access-boundary violations, cross-scope leakage, and jurisdictional correctness.
Production quality and safety are critical. You'll design observability for containment, hallucination rates, tool-selection errors, unsafe actions, and injection vectors, while maintaining privacy by diagnosing issues without exposing restricted HR conversation content. You'll define AI-assisted engineering standards for the domain, converting ambiguous problems into testable specs and holding the line on accountable agent-assisted delivery.
This is hands-on work where it matters: hard integrations, risky migrations, prototypes that settle architectural debates, and incidents that need unblocking. You'll partner across product, engineering, and design to co-create scalable AI solutions.
This is not an ML research role (you do not train foundation models) nor traditional full-stack work. The load-bearing logic lives in natural language—instructions, prompts, context, tool descriptions, guardrails—engineered with the same discipline as code. Correctness is established through evaluation at scale, not fixed assertions.
**Requirements:**
- 7+ 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
