About this role
Workstream needs to bridge the gap in technology for 2.7 billion hourly workers by building AI-native services that deliver completed business outcomes through AI agents and human review. This founding engineer role on the AI-Native Services team will spearhead a new company initiative from zero to one, shaping system architecture and establishing the engineering foundation for future team growth.
The person in this position will build and operate production agents, work closely with design customers on live data, and develop robust evaluation harnesses and human-review layers. Responsibilities also include driving discrepancies to zero during shadow-mode runs, productizing customer-specific workflows into reusable components, and resolving production incidents end to end.
An ideal candidate has personally built and operated production AI agents, possesses strong engineering judgment across models and orchestration, and thrives in ambiguous zero-to-one environments. Someone who communicates clearly with non-technical users and focuses heavily on grounding context and preventing incorrect AI output will do very well here.
What you will do
- Design, build, and operate production agents and agentic workflows incorporating orchestration, tool use, data connections, and deterministic logic.
- Collaborate directly with design customers by embedding within their workflows and building against live data.
- Develop evaluation harnesses including pre-launch thresholds, regression suites, evaluation datasets from real customer work, and post-launch monitoring.
- Construct the human-review layer featuring exception queues, review tooling, escalation paths, and decision auditing.
- Execute shadow-mode parallel runs against existing customer processes and drive discrepancies down to zero before go-live.
- Transform bespoke customer implementations into reusable agents, integrations, and playbooks.
- Manage production incidents end to end and integrate failure insights back into evaluation systems and controls.
What you need
- Personally built and operated at least one AI agent or agentic workflow in a production environment.
- Demonstrated engineering judgment covering models, orchestration, APIs, data integrations, permissions, observability, and evaluations.
- Direct experience working 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 strategies.
- Commitment to preventing incorrect AI output through grounded context, constrained actions, verification, and monitoring.
- Comfort operating in zero-to-one ambiguity with weekly shipping cadences and ownership of outcomes.
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
Is this a remote position?
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 compensation and perks are included?
The role offers a competitive salary and equity, comprehensive health coverage where the company pays 90% of employee premiums and 80% for dependents, a 401K plan, and flexible PTO.
What will I actually own as the first engineer on this team?
You will own the components of the AI-native services, including whether they work, how they fail, and how fast bespoke work becomes reusable. You will not own pricing, deal acceptance, or the margin model.