About this role
Building AI-native services from scratch, designing production agents, and partnering closely with design customers define the daily routine for the new team member. Workstream creates platforms for the hourly workforce and is launching an AI-native services initiative to deliver completed business outcomes through autonomous agents backed by human review. As the initial engineering hire on this new team, the individual shapes the core architecture, manages component reliability, and establishes operational standards alongside leadership.
Operating in a zero-to-one environment requires strong engineering judgment across models, data connections, and deterministic logic. Successful candidates bring hands-on experience deploying functional agentic workflows into production while prioritizing strict controls and continuous evaluation.
What you will do
- Design and operate production agents and agentic workflows covering orchestration, tool use, permissions, and state management.
- Collaborate directly with design customers to map real-world workflows and build solutions against live data.
- Construct comprehensive evaluation harnesses including pre-launch thresholds, regression suites, and post-launch monitoring tools.
- Develop human-review layers consisting of exception queues, escalation paths, and transparent tracing for agent decisions.
- Execute shadow-mode parallel runs against existing customer processes to eliminate discrepancies prior to official go-live.
- Convert bespoke customer use cases into reusable agents, integrations, and operational playbooks.
- Manage production incidents end to end and integrate failure insights directly back into system evaluations and controls.
What you need
- Personally built and operated at least one AI agent or agentic workflow in a production environment.
- Demonstrated strong engineering judgment spanning models, orchestration, APIs, data integrations, and observability.
- Experience working directly with users or customers through discovery, implementation, or incident resolution.
- Ability to decompose messy operational workflows into deterministic steps, agentic decisions, and human exception paths.
- Demonstrated commitment to keeping incorrect AI outputs away from customers through grounded context and verification.
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 will I actually be working on as the first engineer?
You will spearhead a new company initiative from zero to one by building and operating production agents, working forward-deployed with design customers, and establishing evaluation harnesses. You will own the components, determine whether they work, manage failures, and turn customer-specific work into reusable agents.
What kind of background does the team value most?
Demonstrated production experience matters more than title or years. Candidates must have personally built and operated at least one AI agent or agentic workflow in production and possess strong engineering judgment across models, orchestration, APIs, and evaluations.