Senior AI Engineer

Role overview

This is a founding-engineer opportunity to launch a new AI-native services line from zero to one. The team delivers completed business outcomes through AI agents backed by a small human review layer, replacing traditional outsourced service categories at materially better margins. The role carries staff-level scope, a direct line to leadership, and meaningful influence over how the function grows.

Responsibilities

- Design and operate production agents and agentic workflows, including orchestration, tool use, data connections, deterministic logic, state handling, and permissions. - Embed with design customers to map real workflows and build against live operational data. - Build an evaluation harness: real-work eval datasets, pre-launch thresholds, regression suites, and ongoing monitoring. - Construct a human review layer with exception queues, review tooling, escalation paths, and end-to-end audit tracing. - Run shadow-mode parallel executions against each customer's existing process or provider, driving discrepancies to zero before launch. - Convert customer-specific work into reusable agents, integrations, and playbooks so customization stays the exception. - Own production incidents from detection to resolution, feeding every failure back into evals and controls so it cannot recur. - Help set the technical bar as the team scales.

Requirements

- Hands-on experience building and operating at least one AI agent or agentic workflow in production, with the ability to explain how it worked, where it failed, how it was evaluated, and which parts stayed deterministic or human-led. - Strong engineering judgment across models, orchestration, APIs, data, integrations, permissions, observability, and evaluations. - Direct customer or end-user experience in discovery, implementation, or incident resolution, with clear communication for non-technical audiences. - Ability to break a messy workflow into deterministic steps, agentic decisions, human judgment, and exception paths, plus a test plan for each. - Discipline around keeping plausible-but-wrong AI output away from customers through grounded context, constrained actions, verification, evals, review, and monitoring. - Comfort with zero-to-one ambiguity: weekly shipping, ownership of outcomes, and willingness to do unglamorous review tooling and data plumbing.

Nice to have

- Exposure to a regulated domain such as payroll, payments, tax, benefits, or labor compliance. - Production experience weighted more heavily than title or years of tenure.

Benefits and work setup

- Full-time, remote position with occasional in-office visits to support close cross-functional collaboration. - Competitive salary and equity. - Comprehensive medical, dental, and vision coverage, with employer-paid premiums at 90% for employees and 80% for dependents. - 401(k) plan. - Flexible paid time off.