Principal Software Engineer

Description

This is a Principal Software Engineer role in the HR domain, where the work centres on agentic and conversational experiences that act for employees, managers, and HR agents.

The job is not ML research and does not involve training foundation models. Much of the system logic is written in natural language, and behavior is probabilistic, so correctness is checked through large-scale evaluation rather than fixed assertions.

Responsibilities

• Set the technical direction for model-driven features across HR, covering how agents interpret intent, reason over profile, case, catalog, policy, and knowledge context, and act for the user.
• Own the architecture, standards, and evaluation tooling that let several teams ship these experiences safely.
• Design agent decomposition and composition, where reasoning runs, how context is built and limited, how tools are exposed, and how autonomy is granted.
• Make multi-release decisions on model selection and migration, orchestration, build versus adopt, and the cost, latency, and quality trade-offs of each.
• Set domain policy on which HR actions an agent may take, which need a human decision point, and which no agent should attempt. Build mechanisms that keep a human in the loop for pay, employment status, restricted records, and employee-relations matters.
• Treat the shared instruction and tool description layer as a versioned contract for customers who configure, extend, or override it. Provide safe extension points, deprecation paths, and compatibility guarantees.
• Build and maintain evaluation infrastructure: golden datasets, multi-turn test suites, judge calibration, CI gates, and drift detection. Extend it to HR failure cases such as access-boundary violations, cross-scope leakage, and jurisdiction or policy variants.
• Monitor containment, hallucination rate, tool-selection errors, unsafe actions, and injection through user-supplied content. Design diagnostics that work without exposing restricted HR conversation content.
• Turn ambiguous problems into testable specs. Define and enforce standards for accountable agent-assisted delivery, including specifications, review expectations, and verification harnesses.
• Work hands-on where it counts: the hard integration, the risky migration, the prototype that settles a design question, and the incident no one else can resolve.
• Work efficiently with product, engineering, and design to build scalable AI solutions and turn business needs into sound technical designs.

Requirements

• 10+ years of software engineering experience, with technical direction that other teams have adopted.
• Hands-on experience writing agent instructions and prompts, designing autonomous workflows, and building the 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 to production.
• Experience handling entitled data: enforcing per-user access in retrieval and tool layers, separating scope between roles, and handling restricted records under audit.
• Experience building evaluation that other engineers use, including dataset curation, judge calibration, CI gating, and drift detection.
• Strong skills in system design, APIs, data modeling, and testing across front-end, server-side, and relational data, with a high bar for quality.
• Effective and accountable use of AI coding assistants and agents.
• On-call and incident-command experience on customer-facing systems, including owning the systemic fixes that followed.
• Experience with Java, JavaScript/TypeScript, and React, and a proven ability to pick up new tools and frameworks quickly.
• A bachelor's degree in computer science, software engineering, or a related technical field, or equivalent practical experience.
• Preferred: HR domain depth in case management, the employee journey and lifecycle, or payroll, benefits, leave, and absence, enough to set requirements.
• Preferred: experience integrating with core HR, payroll, or benefits systems of record, including reconciliation and eventual-consistency patterns.
• Preferred: experience in a forward deployment model, helping customers adopt the product.

Conditions

Base pay is $221,200 - $387,100 for positions in this location, plus equity where applicable, variable or incentive compensation, and benefits.

The base pay shown is a guideline. Total compensation varies with qualifications, skill level, competencies, and work location, and depends on the geographic location of the role, which may change.

Sales positions generally include an On Target Earnings incentive structure.

Work personas (flexible, remote, or required in office) are assigned based on the nature of the work and the assigned work location.

Eligibility for a work persona may be checked by measuring the distance between your primary residence and the nearest office with a third-party service.

Requisition code: JV21.

Benefits

• Health plans, including flexible spending accounts.
• 401(k) plan with company match.
• Employee stock purchase plan (ESPP).
• Matching donations.
• Flexible time away and family leave programs.