Distinguished Platform Engineer

Quick Facts

• Role: Distinguished Platform Engineer (HR domain AI/agent architecture)

Description

You will set the technical direction for model-driven HR capabilities, including agentic and conversational experiences that interpret intent across employees, managers, and HR agents. You own architecture, standards, and evaluation infrastructure so multiple teams can ship safely—using evaluation at scale rather than fixed assertions. The role is production-focused (not ML research) and emphasizes engineered natural-language behavior, safety boundaries, and operational excellence.

Responsibilities

• Own AI architecture for the HR domain

• Define how agents are decomposed/composed, where reasoning happens, and how context is assembled and bounded

• Determine tool exposure and autonomy delegation, including multi-release model selection/migration and orchestration strategy

• Set the autonomy boundary for HR actions (human-in-the-path for pay, employment status, restricted records, and employee-relations changes)

• Build a versioned shared instruction and tool-description surface with upgrade-safe extension points and deprecation paths

• Establish evaluation infrastructure: golden datasets, multi-turn suites, judge calibration, CI gates, and drift detection

• Cover HR-specific failure classes such as access-boundary violations, cross-scope leakage, and policy/jurisdiction correctness

• Implement production observability for containment, hallucination rate, unsafe tool selection, and injection vectors

• Translate ambiguous needs into testable specs and define verification harnesses and review expectations for accountable delivery

• Lead hard integrations, risky migrations, and prototypes that resolve architectural debates

• Partner with product, engineering, and design to translate business needs into robust technical designs

Requirements

• 13+ years of software engineering with a record of technical direction adopted beyond your immediate team

• 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/function calling, and structured output enforcement (including at least one production migration)

• Entitlement-aware data handling: per-user access enforcement in retrieval/tool layers, role scope separation, and restricted record handling under audit

• Evaluation experience used by other engineers: dataset curation, judge calibration, CI gating, and drift detection

• Strong system design, API, data modeling, and testing skills across front-end, server-side, and relational data with a quality-first mindset

• Ability to use AI coding assistants and agents effectively and accountably

• On-call and incident-command experience on customer-facing systems, including ownership of systemic fixes

• Experience with Java and JavaScript/TypeScript; React experience required, with demonstrated ability to learn new tools/frameworks quickly

• Bachelor’s degree in CS/software engineering or related technical field, or equivalent practical experience

Benefits

• Base pay range: $279,100–$488,400 (plus equity when applicable, variable/incentive compensation, and benefits)

• Health plans including flexible spending accounts

• 401(k) plan with company match

• ESPP

• Matching donations

• Flexible time away plan and family leave programs

• Compensation varies by work location and qualifications and may change