Applied AI Engineer, Internal Systems

Minerva•New York, NY

2d•$186,000 - $236,000•Onsite

About The Position

Minerva is hiring an Applied AI Engineer to build and operate AI agents and automations for the company’s internal teams, including operations, finance, people, recruiting, sales and the founders. Reporting to the COO and working closely with engineering on anything that touches production, this forward-deployed role identifies high-effort or high-risk internal work and replaces it with reliable systems that include audit trails. The position is based in person at Minerva’s Williamsburg, Brooklyn office; candidates must be in New York City or willing to relocate. The engineer will own the company knowledge agent, internal workflow automation, Claude skill library and information source of truth. They will also build the data plumbing for operating dashboards and reporting, establish access controls and human approvals, work directly with internal users to understand their processes, and measure adoption and operating costs. Success is measured by monthly hours of manual work retired, with initial goals including a daily-used Slack knowledge agent, faster new-hire setup and at least three workflows running without a person in the loop.

Requirements

Have shipped agents or automations used by coworkers weekly and be able to demonstrate usage and measurable time savings.
Have production experience with Python or TypeScript and LLMs integrated with real APIs.
Be comfortable with OAuth scopes, webhooks, scheduled jobs and their failure modes.
Understand how companies operate and communicate effectively with recruiters, controllers and security auditors.
Improve processes before automating them.
Apply a controls mindset by deciding who approves actions and what happens when an agent makes a mistake.
Stay current with AI tooling and be able to show a personal setup.
Write clearly enough that people can follow runbooks without assistance.
Be located in New York City or willing to relocate.
Be authorized to work in the United States; visa sponsorship is considered case by case.

Nice To Haves

Experience rolling out Claude or another model platform company-wide, including access, permissions, usage and cost.
Experience participating in a SOC 2 or similar audit, particularly on the evidence-producing side.
Hands-on experience with startup systems such as HRIS, ATS, CRM, billing and spend tools.

Responsibilities

Own the company knowledge agent across documents, Slack, calls and tickets, using Slack as the front end and providing sourced answers.
Automate company processes such as hiring, onboarding and offboarding, access provisioning, vendor reviews, customer security questionnaires, contract renewals and billing.
Run the skill library, connecting Claude to team tools and maintaining skills with named owners, evaluations and appropriate permissions.
Own the source of truth for company information, making information findable to employees and agents and enabling agents to propose updates for human approval.
Build the data plumbing for operating dashboards, metrics, controls and board reporting.
Establish guardrails, including least-privilege access, human approval before agents write to systems of record, and audit trails that can serve as compliance evidence.
Work directly with internal users to observe their workflows and automate the parts they find burdensome.
Measure adoption, usage, model costs and agent access; retire unused systems and write runbooks for retained systems.
Set a baseline and measure the monthly hours of manual work retired.