AI Platform Engineer

About the Role

The AI Platform Engineer builds and runs the application layer that turns raw AI models into safe, governed, production systems, for our clients and for Resolved OS, the platform we run our own business on. A model on its own is not a product; the value and the safety live in the layer around it. You work at the intersection of software engineering, infrastructure, and AI governance, reporting to the CIO.

Key Responsibilities

• Build the Application Layer | Design and build retrieval-augmented systems, tool and Model Context Protocol integrations, guardrails, and the interfaces people actually use, on top of the models we deploy.
• Model Deployment | Stand up and operate models across on-premises and open deployments and commercial APIs like Anthropic and OpenAI, model-agnostic by design.
• Governance & Security | Enforce permissions, data isolation, and auditability so client IP and data stay in bounds, aligned with our Zero Trust posture.
• Infrastructure & Reliability | Own the pipelines, vector stores, containers, and monitoring that keep the platform fast and dependable.
• Client Integration | Connect the application layer into the systems each firm already runs, and support it once it is live.

Qualifications

• Strong software engineering background, with Python and/or TypeScript (Node, Next.js).
• Hands-on experience with LLM APIs, retrieval-augmented generation, and vector databases.
• Experience with tool-calling or the Model Context Protocol, and building around model limitations.
• Comfortable with infrastructure: PostgreSQL, containers, and cloud or on-premises deployment.
• Security-minded, with a real understanding of data isolation and least-privilege access.
• Bonus: self-hosting open models, agentic workflows, or prior MSP or professional-services experience.

Compensation

Competitive, based on experience.

Submit a resume and a short note on something you have built with AI.