Quadrivia is the health technology company behind Q, a comprehensive, controllable, and customizable assistant AI built by clinicians, for clinicians. Addressing the urgent shortage of healthcare professionals, Q provides real-time, personal, and reliable support for clinical tasks across the care continuum. Designed for providers, payers, and pharmaceutical companies, Q is easy to customize and integrates seamlessly into workflows, delivering precise assistance across the care spectrum.
The Role
At Quadrivia, we’re solving the chronic imbalance between the growing demand for healthcare and the constrained supply of clinical skills. While we’re building the world’s most comprehensive clinical assistant externally, internally we’re pioneering a new way to run a company. We believe that by letting AI agents handle the repetitive, necessary tasks that bog down every business, we can free our brilliant minds to focus on what truly matters.
That is where you come in. We’re looking for an AI Automation Engineer to build an ambitious autonomous backbone for our operations. If you’ve spent the last year deep in Skills, workflows, and MCP architectures—orchestrating autonomous flows with Claude, Gemini, and the latest agentic toolchains—and you know exactly where the line sits between a prototype and a production-grade system, you’ve found your team.
What You'll Do
Hunt down high-leverage processes. Talk to people across the company, find the manual, repetitive, error-prone work, and rank it by what's genuinely worth automating.
Pull a workflow out of someone's head and specify it. Most of the job is turning a vague "this is just how we do it" into something precise enough to automate.
Build the automation. Python and API glue, MCP servers and clients, Claude Skills, agent workflows, and small services where they're needed.
Instrument what you ship so it doesn't rot silently. Logs, alerts when something breaks, and a way to know whether the automation is still doing its job.
Drive adoption. Get non-technical teams to trust and use what you've built, train them, and stay close after launch so it sticks.
Know when to escalate. When an automation needs to become real platform, hand it to the backend team instead of bolting on. Knowing where that line sits is part of the job.
Minimum Qualifications
You've automated real business processes end to end, from "what's the actual problem here" through to people using it every day. We'll want to see what you shipped and what it saved.
You're comfortable in front of non-technical teams. You can extract a workflow, push back on a bad priority, and sell a new way of working to people who don't code.
You write code. Python, APIs, scripting, enough to build the automation yourself without waiting on an engineer for every step.
You're fluent in the agentic toolchain (Claude Cowork, Skills, MCP, workflow tools), or you'll obviously get there fast.
You instrument and maintain what you build. You've felt the pain of an automation that broke quietly, and you don't let it happen twice.
Nice to Have
Startup experience, and comfort wearing several hats.
A background as a solutions engineer, technical PM, consultant, or ops engineer who went agentic-native.
Classic RPA exposure (UiPath and similar). Useful for context, as some legacy systems and EHRs can only be accessed via these integration types.
Healthcare or other regulated-industry experience.
Spanish, for the internal teams you'll embed with.
Example Problems You'll Tackle
GTM & Sales Intelligence: Automate CRM updates, call logging, deal qualification, prospect research, and smart alerting to keep the team selling instead of doing admin.
Content: Automate social media workflows, using AI to streamline video generation and post-production editing.
HR: Streamline candidate screening workflows and automate repetitive tasks in the employee onboarding process.
Ops: Map high-effort manual processes, like patient onboarding, and build automations to handle the heavy lifting.
Platform: Graduate successful scripts into the core backend platform whenever an automation outgrows its initial scope.
Tech Stack
Python, REST and webhook integrations, MCP, Claude Skills and Cowork, agent and workflow orchestration, plus whatever automation tooling fits the job. You'll lean on the AI platform (Cortex) for anything heavy, and pick up new tools about as fast as they ship.
What Success Looks Like
Measurable hours given back across the company, on the processes people used to dread.
The teams you work with reach for automation by default and trust it, because the things you ship keep working.
Your automations are instrumented and maintained, not a graveyard of scripts nobody dares touch.
Quadrivia runs leaner than its headcount suggests, and you're a big reason why.
Skills Required
- Automated real business processes end-to-end and can demonstrate shipped automations and saved hours.
- Comfortable presenting to and extracting workflows from non-technical teams; ability to drive adoption.
- Write code (Python), build API integrations and scripting to implement automations.
- Fluency with agentic toolchain (Claude Cowork, Claude Skills, MCP, workflow tools) or ability to learn quickly.
- Instrument and maintain automations with logs, alerts, and monitoring to prevent silent failures.
- Startup experience and comfort wearing several hats.
- Background as a solutions engineer, technical PM, consultant, or ops engineer who adopted agentic tooling.
- Classic RPA exposure (UiPath or similar) for legacy systems and EHR integrations.
- Healthcare or other regulated-industry experience.
- Spanish language skills for internal team embedding.
What We Do
Quadrivia is building Qu, a personal clinical assistant with wide capabilities across the care spectrum. It is designed by clinicians for clinicians, and the communities we serve. According to the World Health Organization, there is a global shortfall of up to 18 million healthcare workers. A root cause of the worldwide challenge with the quality, accessibility and affordability of healthcare is this structural imbalance between elastic demand by population and constrained supply of providers. Care is delivered globally in many different ways. By making Qu comprehensive, controllable and customizable, we aim to help healthcare professionals be in control of AI’s utility, safety and quality. Qu’s cognitive architecture of expanding agents is designed to support clinicians not just for a single task but across the full stack of routine clinical and administrative tasks, patient interactions, decision-making, chronic and post operative care, continuous monitoring and support, in multiple languages.
