About this role
Building AI-native services from zero to one involves partnering directly with design customers to map messy workflows and construct production-grade agents against live data. Engineering responsibilities include designing evaluation harnesses, developing human-review layers with exception queues, and operating production agentic workflows that handle orchestration, tool use, and deterministic logic.
Workstream is launching a new AI-Native Services initiative to deliver completed business outcomes for the hourly workforce through AI agents backed by a small human review layer. As the first engineer on this team, the hire will spearhead technical architecture, establish engineering standards, and shape the foundation for incoming team members.
Ideal candidates bring a track record of personally deploying and operating production AI agents while possessing strong engineering judgment across models, APIs, and observability. Someone who thrives in ambiguity and prioritizes reliability over novelty will excel in this position.
What you will do
- Build and operate production-ready agents and agentic workflows incorporating orchestration, tool use, data connections, and deterministic logic.
- Work directly with design customers to map real-world workflows and build solutions against live operational data.
- Develop evaluation harnesses including regression suites, pre-launch thresholds, and post-launch monitoring tools.
- Construct the human-review layer featuring exception queues, escalation paths, and auditing traces.
- Execute shadow-mode parallel runs against legacy processes to resolve discrepancies prior to go-live.
- Transform custom client solutions into scalable, reusable agents, integrations, and playbooks.
- Manage production incidents end to end and integrate failure insights directly into evaluation frameworks.
What you need
- Must have hands-on experience building and operating at least one AI agent or agentic workflow in a production environment.
- Demonstrate strong engineering judgment spanning models, orchestration, APIs, data integrations, and permissions.
- Possess direct experience collaborating with customers or end users through discovery, implementation, or support.
- Ability to decompose unstructured workflows into deterministic steps, agentic choices, and human review boundaries.
- Show a commitment to preventing erroneous AI outputs via grounded context, strict constraints, and rigorous evaluation.
Nice to have
- Exposure to a regulated domain such as payroll, payments, tax, benefits, or labor compliance
Benefits
- Competitive salary and equity
- Comprehensive health coverage including medical, dental, and vision with 90% employer-paid premiums for employees
- In-office amenities and stocked kitchen
- 401K Plan
- Flexible PTO
Questions candidates ask
What stage is the company at?
Workstream is a high-growth Series B company backed by investors including Founders Fund, BOND, and Coatue. The organization is rapidly expanding its product portfolio to serve the hourly workforce.
What is the focus of the new AI initiative?
The AI-Native Services team builds mature service categories delivered by AI agents plus a small human review layer. The initiative aims to deliver completed business outcomes at materially better margins than traditional alternatives.
What will the first engineer own versus other departments?
The engineer will own the technical components, their reliability, failure modes, and the transition of bespoke work into reusable assets. Pricing, deal acceptance, and the margin model sit with the Head of Delivery and the Head of GTM.