SlipstreamJobsFresh Startup & VC-Backed Jobs

Founding Engineer

Workstream - Lehi, UT, United States - Hybrid - posted 2026-08-19

Apply on the company site

SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.

Workstream is a Series B, venture-backed HR, payroll, and hiring platform purpose-built for the hourly workforce (2.7 billion workers globally). The company serves leading brands including Burger King, Carl's Jr./Hardee's, IHOP, and KFC, and is backed by Founders Fund, BOND, and Coatue. You will be the first engineering hire on the AI-Native Services delivery team, 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 AI agents, integrations, evaluation systems, and human-review tooling that deliver completed business outcomes at better margins than traditional alternatives. Key responsibilities: - Build and operate production agents and agentic workflows, including orchestration, tool use, data connections, deterministic logic, state management, and permissions - Work forward-deployed with design customers to understand messy real-world workflows and build against live data - Develop evaluation harnesses: create eval datasets from real customer work, set pre-launch thresholds, build regression suites, and implement post-launch monitoring - Build the human-review layer: exception queues, review tooling, escalation paths, and complete tracing for agent decision auditability - Run shadow-mode parallel runs against existing customer processes to drive discrepancies to zero before go-live - Productize customer-specific work into reusable agents, integrations, and playbooks - Handle production incidents end-to-end and feed failures back into evals and controls - Help set technical standards as the team grows You must have personally built and operated at least one AI agent or agentic workflow in production, with clear understanding of how it worked, where it failed, evaluation approaches, and what remained deterministic or human-led. This is a full-time, hybrid role with 1-2 days per week in-office for cross-functional collaboration.

Similar roles