SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Workstream is a Series B, mission-driven HR, payroll, and hiring platform purpose-built for the hourly workforce. The company serves 2.7 billion hourly workers globally and counts leading brands like Burger King, KFC, IHOP, and Culvers among its customers. Backed by Founders Fund, BOND, and Coatue, Workstream is expanding its product portfolio to deliver AI-native services that automate mature business processes with AI agents plus a small human review layer.
You will be the first engineering hire on the delivery team for AI-native services, reporting to the Head of Delivery. This is a forward-deployed builder role where you embed with design customers, map their real workflows, and build production agents, integrations, evaluations, and review tooling that turn work into a reliable, repeatable service. You will see your systems do real work with real consequences—and own the outcomes when they misbehave.
Key responsibilities include:
- Build and operate production agents and agentic workflows: orchestration, tool use, data connections, deterministic logic, state, and permissions
- Work forward-deployed with design customers, sitting in their workflow and mapping messy reality against live data
- Build evaluation harnesses: datasets from real customer work, pre-launch thresholds, regression suites, and post-launch monitoring
- Build the human-review layer: exception queues, review tooling, escalation paths, and auditable tracing for every agent decision
- Run shadow-mode parallel runs against the customer's existing process and drive discrepancies to zero before go-live
- Turn customer-specific work into reusable agents, integrations, and playbooks—productization is the default
- Handle production incidents end to end and feed every failure back into evals and controls
- Help set the technical bar as the team grows
You will not own pricing, deal acceptance, or the margin model—those sit with the Head of Delivery and Head of GTM. You own the components: whether they work, how they fail, and how fast bespoke work becomes reusable.
This is a full-time, hybrid position with 1–2 days per week in-office to support close cross-functional collaboration.
REQUIREMENTS:
- You have personally built and operated at least one AI agent or agentic workflow in production. You can clearly explain how it worked, where it failed, how you evaluated it, and what you kept deterministic or human-led.
- Strong engineering judgment across models, orchestration, APIs, data and integrations, permissions, observability, and evaluations.
- You have worked directly with customers or end users—discovery, implementation, or incident resolution—and communicate clearly with non-technical people.
- You can break a messy workflow into deterministic steps, agentic decisions, human judgment, and exception paths—and define how each part will be tested.
- You care about keeping plausible but wrong AI output away from customers: grounded context, constrained actions, verification, evals, review, monitoring.
- You thrive in zero-to-one ambiguity: shipping weekly, owning outcomes, and doing whatever the service needs—including unglamorous review tooling and data plumbing.
- Exposure to a regulated domain (payroll, payments, tax, benefits, labor compliance) is a plus, not a requirement.
- Demonstrated production experience matters more than title or years.
