Distinguished Platform Engineer

ServiceNow•Santa Clara, CA

About The Position

As a Distinguished Engineer in HRSD, you set the technical direction for model-driven capabilities across the HR domain, including agentic and conversational experiences that interpret employee, manager, and HR agent intent, reason over profile, case, catalog, policy, and knowledge context, and act on users’ behalf. Your scope is the architecture, standards, and evaluation infrastructure that enable multiple teams to ship these experiences safely, rather than ownership of a single feature set. This is not an ML research role; the position does not train foundation models. It is also distinct from traditional deterministic full-stack engineering: natural-language instructions, prompts, context, tool descriptions, and guardrails must be engineered with the discipline applied to code, while probabilistic behavior requires evaluation at scale rather than fixed assertions. The role owns domain AI architecture and multi-release decisions, including agent composition, reasoning and context boundaries, tool exposure, autonomy delegation, model selection and migration, orchestration, build-versus-adopt choices, and cost, latency, and quality tradeoffs. It defines HR autonomy policy and builds structural safeguards so sensitive actions—such as changes to pay or employment status, access to restricted records, and employee-relations matters—have appropriate human decision points or are not attempted by agents. The position also owns the shared, customer-configurable instruction and tool-description surface as a versioned product contract, including upgrade-safe extension points, deprecation paths, and compatibility guarantees. It establishes evaluation infrastructure such as golden datasets, multi-turn suites, judge calibration, CI gates, and drift detection, with coverage for HR-specific risks including access-boundary violations, cross-scope leakage, and jurisdictional or policy-variant correctness. It designs production observability and safety measures for containment, hallucination, tool-selection errors, unsafe actions, and prompt-injection vectors, while ensuring diagnosis does not expose restricted HR conversation content. The Distinguished Engineer sets standards for accountable AI-assisted engineering, including specifications, reviews, and verification harnesses. The role is hands-on for difficult integrations, risky migrations, architectural prototypes, and incidents that require escalation. It partners with product, engineering, and design to translate business needs into scalable AI solutions and robust technical designs.

Requirements

13+ years of software engineering experience, with a record of technical direction adopted beyond the immediate team.
Direct, hands-on experience authoring agentic instructions and prompts, designing autonomous workflows, and building evaluations to verify them.
Production experience with LLM APIs, retrieval-grounded features, agent orchestration, tool and function calling, and structured output enforcement.
Experience carrying at least one model or orchestration migration through production.
Experience with entitlement-aware data handling, including per-user access enforcement in retrieval and tool layers, role-based scope separation, and handling restricted records under audit.
Evaluation experience used by engineers beyond oneself, including dataset curation, judge calibration, CI gating, and drift detection.
Strong command of system design, APIs, data modeling, and testing across front-end, server-side, and relational data work, with a high-quality mindset.
Effective and accountable use of AI coding assistants and agents.
On-call and incident-command experience on customer-facing systems, including ownership of resulting systemic fixes.
Experience with Java, JavaScript/TypeScript, and React, and demonstrated ability to learn new tools and frameworks quickly.
Bachelor’s degree in computer science, software engineering, or a related technical field, or equivalent practical experience.

Nice To Haves

HR domain depth in case management, employee journeys and lifecycle, or payroll, benefits, leave, or absence sufficient to set requirements.
Experience integrating 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.

Responsibilities

Set AI architecture and technical direction for model-driven capabilities across the HR domain.
Determine agent decomposition and composition, where reasoning occurs, how context is assembled and bounded, how tools are exposed, and how autonomy is delegated.
Make multi-release decisions about model selection and migration, orchestration, build-versus-adopt, and cost, latency, and quality tradeoffs.
Define domain policy for which HR actions agents may take, which require human decisions, and which agents must not attempt; build structural safeguards for sensitive actions and records.
Own the shared instruction and tool-description surface as a versioned contract, including upgrade-safe extension points, deprecation paths, and compatibility guarantees.
Own evaluation infrastructure, including golden datasets, multi-turn suites, judge calibration, CI gates, drift detection, and HR-specific failure coverage.
Design production observability and safety for containment, hallucinations, tool-selection errors, unsafe actions, and injection vectors, while protecting restricted HR conversation content during diagnosis.
Define standards for accountable agent-assisted engineering, including specification standards, review expectations, and verification harnesses.
Contribute hands-on to difficult integrations, risky migrations, architectural prototypes, and incidents that others cannot unblock.
Partner with product, engineering, and design to create scalable AI solutions and translate business needs into robust technical designs.
Own systemic fixes following incidents on customer-facing systems.