Staff AI Data Engineer

• Driven by outcomes: You care about helping operations, GTM, product, and engineering teams move faster, make higher-quality data-driven decisions, and build AI-powered workflows with confidence. You measure success in reduced friction, improved signal reliability, and meaningful business impact — not just infrastructure shipped. • AI-native. You understand how LLMs interpret data and design retrieval, evaluation, and observability into systems from the start. • A product-driving technical leader. You define what data should exist, how it should be structured, and how AI should safely interact with it to drive workflow improvements. • Deep in data modeling and system design. You design schemas, contracts, and storage strategies that enable AI reasoning across domains, not just analytics queries. • Thoughtful about safety and privacy. You build AI-aware data systems with governance, access control, and auditability as first-class concerns. • In this role, you will own AI-powered improvements in core brightwheel workflows end-to-end, with particular emphasis on the data foundation that enables those workflows. You will: • Ship “virtual employee” workflows that do real work before humans engage: research, verification, prioritization, deduplication, and prep artifacts that cite evidence and flag unknowns. • Design and build a durable job execution system for agent workflows, including retries, explicit budgets, idempotency, and monitoring. • Build evidence-first AI pipelines that produce structured outputs with provenance and uncertainty handling, and that store artifacts and evidence rather than overwriting truth. • Design data foundations that allow AI to stitch together longitudinal operational signals across domains (customers, prospects, interactions, transcripts, product/ops/billing/support signals) into reliable workflows. • Create shared abstractions and tooling for AI and data systems: tool interfaces, logging, cost tracking, evaluation harnesses, and reusable workflow components. • Establish data contracts, SLAs, observability, and auditability practices that increase trust in both data and AI outputs. • Partner with internal teams as customers to define success metrics, design workflow delivery surfaces, and iterate quickly based on adoption and impact. • Lead by example in AI-augmented engineering, using AI tools to increase velocity while maintaining architectural rigor. • What You’ve Done • We are open to a variety of backgrounds, but you likely bring: • 5+ years of professional engineering experience with clear ownership of production systems from design doc through launch and iteration. • A track record of shipping AI-powered workflows to production with measurable impact. • Hands-on experience with LLM systems in real applications, including tool use, retrieval-style patterns, evaluation, and monitoring. • Experience designing data platforms for operational use cases: canonical models, identity resolution/deduplication, and governance patterns that support safe downstream consumption. • Experience designing reliable workflow systems: job orchestration, backfills/retries, observability, and cost/performance tradeoffs. • Experience designing lakehouse or warehouse architectures that support both analytics and AI workloads, with thoughtful cost and performance tradeoffs. • Hands-on experience implementing vector indexing, embedding pipelines, or hybrid structured + semantic retrieval systems in production. • Experience building event-driven or real-time data architectures that support operational intelligence, not just batch reporting. • Background in vertical SaaS, CRM, or operations-heavy domains where operational data is central to product differentiation. • Experience building internal data platforms or shared services adopted across multiple engineering teams. • Experience defining data governance frameworks, PII handling standards, and auditability patterns in AI-enabled systems. • Demonstrated ability to influence technical strategy at Staff or Principal level across organizational boundaries. • Data foundations: relational databases and operational data platforms; canonical entity modeling; identity resolution/deduplication; data contracts and SLAs. • Workflow execution: job queues, schedulers, durable retries, and event-driven systems for bounded, measurable work. • AI systems: hosted LLMs, tool calling, retrieval patterns, and evaluation/monitoring tooling. • Observability and governance: logging standards, lineage/traceability patterns, access controls, privacy-aware designs, and auditability. • We value architectural judgment over attachment to specific tools. The right candidate can reason about tradeoffs across reliability, correctness, latency, and cost in AI-native systems.