Platform Engineer, AI Systems
Platform engineering role across Python, TypeScript, backend services, multi-tenant systems, AI infrastructure, and release foundations
About Agency Intelligence
We're built by agency founders who understand the chaos. Teams adopt AI piecemeal, with different tools, different prompts, and little visibility into usage, cost, or ROI.
Our platform is three parts: ai/OS manages routing, access, governance, and cost controls. ai/Tools is where work happens across chat, agents, apps, and integrations. ai/Dashboard shows usage, cost, and ROI.
We're building products agencies use in real workflows, not generic AI demos. As a Platform Engineer, AI Systems, you'll build the shared foundations that let those products scale reliably across tenants, environments, and AI systems.
The role
You'll own shared platform systems across backend services, multi-tenant architecture, AI infrastructure, access controls, observability, and release plumbing. This is a hands-on role for an engineer who likes building the systems that make fast product development possible.
You should be strong in backend and systems work, comfortable with Python and/or TypeScript services, and able to improve reliability without slowing the team down. You should care about architecture, production readiness, and keeping technical foundations clean as the product surface grows.
This is an early engineering role with direct ownership and close partnership with the Head of Engineering and product engineering.
What you'll do
- 1
Own core platform systems
Design and maintain shared backend foundations that support chat, workflows, apps, dashboards, and integrations.
- 2
Build multi-tenant and access foundations
Own tenant isolation, access controls, governance patterns, and the systems needed to support secure customer environments.
- 3
Support AI infrastructure
Extend Python-based services, RAG layers, ingestion flows, model or provider plumbing, and the backend systems that power AI features.
- 4
Improve reliability and observability
Strengthen production readiness with better monitoring, logging, deployment foundations, and internal tooling.
- 5
Reduce shared technical friction
Make product engineers faster by improving platform clarity, stability, and reuse.
What we're looking for
Core Skills
- Strong backend and systems engineering experience in production environments
- Experience designing APIs, services, and shared technical systems
- Experience with Python and/or TypeScript backend work
- Comfortable owning technical problems end to end through production
Platform and Systems
- Experience with multi-tenant systems, access controls, or environment isolation
- Experience with deployment systems, Docker, managed infrastructure, and backend services
- Strong understanding of data flow, service boundaries, and operational reliability
- Comfortable working on internal tooling and shared platform capabilities
AI Infrastructure
- Experience with LLM integrations, RAG systems, ingest pipelines, model routing, or related AI infrastructure
- Familiarity with vector search or embedding-based systems
- Comfortable working on API-driven AI services and backend support systems
- Familiarity with observability, logging, or release automation
Nice-to-Have
- Experience with Railway, Vercel, AWS, or similar infrastructure platforms
- Experience with MongoDB, PostgreSQL, or vector-enabled data layers
- Familiarity with security and governance in AI-enabled products
- Familiarity with agency, SaaS, or multi-tenant product environments
Team Skills
- Strong communication across technical and non-technical teams
- Self-starter who owns problems end to end and improves the team around them
Tech stack
You don't need to know everything on day one. Core stack: Python, TypeScript, Node.js, MongoDB, PostgreSQL, Docker, Railway, and AI model APIs.
Backend Services
Data and Infrastructure
AI and Platform Systems
Team & culture
High ownership
Own important systems that multiple products depend on.
Small and direct
Work directly with the Head of Engineering. Fast decisions. Clear technical ownership.
Real production responsibility
Your work affects platform reliability, scale, and how quickly the team can ship.
Remote first
Work from home with flexible hours within US time zones.
Ready to build?
If you like building the systems behind AI products, care about architecture and reliability, and want to shape the platform that multiple products run on, we should talk.