Principal Software Engineer

Description

Principal Software Engineer role on the HR domain team, job code JV21.

The team builds an HR product that customers configure, extend, and override on their own instances.

This is not a machine learning research role and you will not train foundation models. The work is also different from typical full-stack work because the behavior is probabilistic and much of the core logic is written in natural language.

Your ownership covers the architecture, standards, and evaluation infrastructure that let several teams release agentic and conversational features safely, rather than one feature set.

Responsibilities

• Set the technical direction for AI agents that understand employee, manager, and HR agent requests, reason over profile, case, catalog, policy, and knowledge data, and take actions for the user.
• Design the domain's AI architecture: how agents are split and combined, where reasoning runs, how context is built and limited, how tools are exposed, and how much autonomy is granted.
• Make the multi-release decisions on model selection and migration, orchestration approach, build versus adopt, and the cost, latency, and quality trade-offs of each.
• Decide which HR actions an agent may perform, which need a human decision point, and which no agent should attempt. Build mechanisms so that changes to pay, employment status, restricted records, or employee relations always include a human.
• Treat the shared instruction and tool description layer as a versioned contract, with upgrade-safe extension points, deprecation paths, and compatibility guarantees for customers.
• Own the golden datasets, multi-turn test suites, judge calibration, CI gates, and drift detection that let teams change behavior safely. Extend coverage to HR failure types such as access-boundary violations, cross-scope leakage, and jurisdiction or policy variant errors.
• Build observability for containment, hallucination rate, tool selection errors, unsafe actions, and injection through user-supplied content in agent context. Design diagnosis that works without exposing HR conversation content, which is restricted.
• Turn unclear problems into testable specs. Define and enforce standards for accountable agent-assisted delivery, including specification, review, and verification.
• Get hands on where it matters: difficult integrations, risky migrations, prototypes that settle architecture debates, and incidents no one else can resolve.
• Work 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, including technical direction that other teams adopted.
• Hands-on experience writing agent instructions and prompts, designing autonomous workflows, and building the evaluation that checks 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 taken to production.
• Experience handling entitlements in data: enforcing per-user access in retrieval and tool layers, separating scope between roles, and handling restricted records under audit.
• Experience building evaluations 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, and relational data, with a strong focus on 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.
• Bachelor's degree in computer science, software engineering, or a related technical field, or equivalent practical experience.
• Preferred: depth in HR domain areas such as case management, employee 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: contribution to a forward deployment model that champions customer adoption.

Conditions

Base pay for this location is $199,100 to $348,400, plus equity where applicable, variable or incentive compensation, and benefits.

Sales positions generally include an On Target Earnings incentive structure. The base pay shown is a guideline, and total compensation depends on qualifications, skill level, competencies, and work location.

Pay depends on the geographic location of the role and may change based on work location.

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

To confirm eligibility for a work persona, the company may measure the distance between your main residence and the nearest office using a third-party service.

Benefits

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