About this role
Workstream is building AI-native services that deliver completed business outcomes through AI agents and a human review layer for the hourly workforce. As the first engineer on the AI-Native Services team, the successful candidate will spearhead a new company initiative from zero to one by shaping its architecture, setting the engineering standard, and building out future team members. The person in this role will work forward-deployed with design customers, operate production agents and agentic workflows, build evaluation harnesses and human-review layers, and transform customer-specific work into reusable agents.
This founding engineer position sits at a high-growth Series B company backed by prominent venture capital firms. Ideal candidates possess hands-on experience building and operating production AI agents, strong engineering judgment across models and orchestration, and comfort with zero-to-one ambiguity. The position offers a direct line to leadership and real influence over product growth in a mission-driven environment focused on underserved hourly workers.
What you will do
- Build and operate production agents and agentic workflows covering orchestration, tool use, data connections, deterministic logic, state, and permissions.
- Work forward-deployed with design customers by embedding in their workflows, mapping messy realities, and building against live data.
- Develop evaluation harnesses including eval datasets from real customer work, pre-launch thresholds, regression suites, and post-launch monitoring.
- Construct the human-review layer consisting of exception queues, review tooling, escalation paths, and tracing for auditable agent decisions.
- Execute shadow-mode parallel runs against existing customer processes and drive discrepancies to zero prior to go-live.
- Transform customer-specific work into reusable agents, integrations, and playbooks where productization serves as the default.
- Manage production incidents end to end and feed failures back into evaluations and controls to prevent recurrence.
What you need
- Personally built and operated at least one AI agent or agentic workflow in a production environment.
- Demonstrated strong engineering judgment across models, orchestration, APIs, data integrations, permissions, observability, and evaluations.
- Experience working directly with customers or end users spanning discovery, implementation, or incident resolution.
- Ability to decompose messy workflows into deterministic steps, agentic decisions, human judgment, and exception paths with defined testing methods.
- Commitment to keeping incorrect AI output away from customers through grounded context, constrained actions, verification, evaluations, and monitoring.
- Comfort thriving in zero-to-one ambiguity by shipping weekly, owning outcomes, and handling all necessary tasks from review tooling to data plumbing.
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% of premiums paid for employees and 80% for dependents
- 401K Plan
- Flexible PTO
Questions candidates ask
What is the remote work policy?
This is a full-time, remote position with occasional in-office visits as needed to support close cross-functional collaboration and key team initiatives.
What kind of team will I be joining?
You will be the first engineer on Workstream's AI-Native Services team, serving in a founding engineer opportunity to spearhead a new company initiative from zero to one.
What will I actually own in this role?
You will own the components of the AI services, including whether they work, how they fail, and how fast bespoke work becomes reusable, while pricing and margin models sit with leadership.