Staff Software Engineer

Description

The company builds AI-driven HR experiences: conversational and agentic tools that understand what employees, managers and HR agents want, draw on profile, case, catalog, policy and knowledge data, and act for the user.

This role sets technical direction for the architecture, standards and evaluation infrastructure that several teams use to ship these experiences safely. It is not an ML research role and does not involve training foundation models. It is also different from traditional full-stack staff work, because much of the core logic is written in natural language and behavior is probabilistic, so correctness is proven through large-scale evaluation rather than fixed assertions.

Title: Staff Software Engineer

Responsibilities

• Design the AI architecture for the HR domain: how agents are split up and combined, where reasoning runs, how context is built and limited, how tools are exposed, and how much autonomy is granted.
• Make multi-release decisions on model selection and migration, orchestration approach, build versus adopt, and the cost, latency and quality trade-offs of each.
• Set domain policy on which HR actions an agent may take alone, 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 matters always include a human.
• Treat the shared instruction and tool description surface as a versioned contract that customers can configure, extend and override on their own instances. Provide upgrade-safe extension points, deprecation paths and compatibility guarantees.
• Own the evaluation infrastructure: golden datasets, multi-turn suites, judge calibration, CI gates and drift detection that let teams change behavior safely. Cover HR-specific failure classes, including access-boundary violations, cross-scope leakage, and jurisdiction- and policy-variant errors.
• Monitor production quality and safety, including containment, hallucination rate, tool-selection errors, unsafe actions and injection through user-supplied content in agent context. Because HR conversations are restricted, build diagnostics that work without exposing what was said.
• Turn unclear problems into testable specs. Define and enforce standards for accountable agent-assisted delivery in the domain, including specification, review and verification practices.
• Get hands-on where it counts: the difficult integration, the risky migration, the prototype that settles an architecture debate, and the incident 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

• Have 7+ years of software engineering experience, including technical direction that other teams adopted.
• Have hands-on experience writing agent instructions and prompts, designing autonomous workflows, and building the evaluations that check them.
• Have 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.
• Know how to enforce per-user access in retrieval and tool layers, separate scope between roles, and handle restricted records under audit.
• Have built evaluations that other engineers used: dataset curation, judge calibration, CI gating and drift detection.
• Have strong skills in system design, APIs, data modeling and testing across front-end, server-side and relational data, with a strong focus on quality.
• Use AI coding assistants and agents effectively and take accountability for the results.
• Have been on call and led incident response for customer-facing systems, and owned the systemic fixes that followed.
• Have experience with Java, JavaScript/TypeScript and React, and can learn new tools and frameworks quickly.
• Hold a bachelor's degree in computer science, software engineering or a related technical field, or have equivalent practical experience.
• Preferred: HR domain knowledge in case management, employee lifecycle, or payroll, benefits and leave/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.
• Preferred: FD21.

Conditions

Base pay for this role is $166,500 - $291,400, plus equity where applicable, variable or incentive compensation and benefits. The base pay shown is a guideline; total compensation depends on qualifications, skill level, competencies and work location. Pay is based on the location where the role sits and may change with it.

Work personas (flexible, remote or required in office) are assigned by the nature of the work and work location. To confirm eligibility, the company may measure the distance between your home and the nearest office using a third-party service.

Equal opportunity applies; accommodations are available on request.

Benefits

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