Distinguished Platform Engineer

ServiceNow•Santa Clara, CA

18h•$279,100 - $488,400

About The Position

The Principal Engineer in HRSD sets 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. The role owns architecture, standards, and evaluation infrastructure that enable multiple teams to ship these experiences safely, rather than owning a single feature set. This is not an ML research position and does not involve training foundation models. The work treats natural-language instructions, prompts, context, tool descriptions, and guardrails with the rigor of code, while establishing correctness for probabilistic behavior through evaluation at scale. The engineer owns domain AI architecture and multi-release decisions, including agent composition, context assembly, tool exposure, autonomy delegation, model selection and migration, orchestration, build-versus-adopt choices, and cost, latency, and quality tradeoffs. The role defines structural boundaries for agent autonomy, ensuring that actions affecting pay, employment status, restricted records, or employee-relations matters require human involvement. The position also owns the shared, versioned instruction and tool-description surface, 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, drift detection, and coverage for HR-specific failures. It designs production observability and diagnosis for quality and safety while protecting restricted HR conversation content, and sets standards for accountable AI-assisted engineering. The engineer remains hands-on for critical integrations, migrations, prototypes, and incidents, and partners with product, engineering, and design to develop scalable AI solutions and robust technical designs.

Requirements

10+ years of software engineering experience.
A record of technical direction adopted beyond the candidate’s immediate team.
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 audited handling of restricted records.
Evaluation experience used by other engineers, 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.
A high-quality engineering mindset.
Effective and accountable use of AI coding assistants and agents.
On-call and incident-command experience on customer-facing systems, including ownership of subsequent 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 technical direction and own AI architecture for model-driven HR-domain capabilities and agentic experiences.
Determine agent decomposition and composition, reasoning boundaries, context assembly and limits, tool exposure, and delegation of autonomy.
Make multi-release decisions on model selection and migration, orchestration, build-versus-adopt, and cost, latency, and quality tradeoffs.
Define domain policies and structural mechanisms governing which HR actions agents may take, which require human decisions, and which agents must not attempt.
Own the shared instruction and tool-description surface as a versioned product contract, including upgrade-safe extension points, deprecation paths, and compatibility guarantees.
Build and maintain evaluation infrastructure, including golden datasets, multi-turn test suites, judge calibration, CI gates, and drift detection.
Extend evaluation coverage to HR-specific failures such as access-boundary violations, cross-scope leakage, and jurisdictional or policy-variant errors.
Design production observability for containment, hallucination rates, tool-selection errors, unsafe actions, and prompt-injection vectors.
Develop diagnostic approaches that protect the restricted content of HR conversations.
Define AI-assisted engineering specifications, review expectations, and verification harnesses, and uphold these standards across the domain.
Contribute hands-on to difficult integrations, risky migrations, architectural prototypes, and incidents requiring senior technical ownership.
Collaborate with product, engineering, and design to co-create scalable AI solutions and translate business needs into technical designs.
Own systemic fixes following incidents on customer-facing systems.