Founding Engineer

About the Role

Workstream is building AI-native services that deliver completed business outcomes, focusing on mature service categories businesses already pay for. These services are delivered by AI agents with a small human review layer, offering better margins than traditional alternatives. We are currently validating the first service with design customers from our existing base. As the first engineering hire on the delivery team, you will play a crucial role in embedding with design customers, mapping their workflows, and building production agents, integrations, evaluations, and review tooling to ensure reliable and repeatable services.

Responsibilities

• Build and operate production agents and agentic workflows, including orchestration, tool use, data connections, deterministic logic, state, and permissions.
• Work forward-deployed with design customers to map their workflows and build solutions using live data.
• Develop the evaluation harness, including eval datasets, pre-launch thresholds, regression suites, and post-launch monitoring.
• Create the human-review layer, encompassing exception queues, review tooling, escalation paths, and auditable agent decision tracing.
• Run shadow-mode parallel runs against existing customer processes to eliminate discrepancies before go-live.
• Transform customer-specific work into reusable agents, integrations, and playbooks, prioritizing productization over customization.
• Manage production incidents end-to-end and incorporate learnings into evaluations and controls to prevent recurrence.
• Help establish the technical bar and standards as the team grows.

Requirements

• Proven experience building and operating at least one AI agent or agentic workflow in production, with the ability to explain its functionality, failures, evaluation methods, and human-led components.
• Strong engineering judgment across models, orchestration, APIs, data integrations, permissions, observability, and evaluations.
• Direct experience working with customers or end-users in discovery, implementation, or incident resolution, with clear communication skills for non-technical stakeholders.
• Ability to decompose messy workflows into deterministic steps, agentic decisions, human judgment, and exception paths, with defined testing strategies.
• Focus on preventing incorrect AI output through grounded context, constrained actions, verification, evaluations, review, and monitoring.
• Comfort with zero-to-one ambiguity, shipping weekly, owning outcomes, and handling unglamorous tasks like review tooling and data plumbing.
• Exposure to regulated domains (e.g., payroll, payments, tax, benefits, labor compliance) is a plus but not required.
• Demonstrated production experience is valued over title or years of experience.

Qualifications

Not explicitly stated in the posting, but implied through the requirements.

Skills

• AI agent development and operation
• Workflow orchestration and integration
• Customer collaboration and communication
• Evaluation and monitoring of AI systems
• Incident management and resolution
• Productization of bespoke solutions

Benefits

• Competitive salary and equity
• Comprehensive health coverage: medical, dental, and vision (95% premiums paid for employees, 85% for dependents)
• In-office amenities and stocked kitchen
• 401K Plan
• Pre-tax commuter benefits
• Flexible PTO

About Workstream

Workstream is a mission-driven company building an all-in-one HR, payroll, and hiring platform for the hourly workforce. With 2.7 billion hourly workers globally, this underserved market deserves better technology. Workstream serves leading brands across multiple sectors, including Burger King, Carl's Jr./Hardee's, IHOP, KFC, and Culvers. As a high-growth Series B company, we are expanding our product portfolio to empower deskless workers and local businesses. Backed by top VCs like Founders Fund, BOND, and Coatue, we are committed to delivering innovative solutions for the hourly workforce.

For more information, visit: Series B Funding Announcement, TechCrunch Feature, TechBuzz News.