← Back to workFP Complete · VP Platform Engineering, AI R&D

Multi-Model Agent Platform

Problem

Client AI initiatives were slow to ship: model deployment was manual, onboarding new engineers took weeks, and there was no secure, shared substrate for running multi-model LLM and agent workloads in production. Every team was re-inventing the unsafe parts — auth, cost control, deploys — instead of shipping product.

Architecture

A Kubernetes/AWS platform running multi-model LLM and generative-AI pipelines, fronted by SSO-secured agent infrastructure and an internal developer platform with self-service onboarding. Standardized CI/CD on GitHub Actions, with SLAs, incident-response processes, and full observability (Prometheus, Grafana, OpenTelemetry).

Approach

I treated the platform as a product with internal customers, not a pile of bespoke pipelines. One secured, model-agnostic substrate: a self-service portal for onboarding, an orchestration layer with MCP tooling and Rust agent runtimes, and governance — SSO, per-team cost attribution, and an audit trail — baked in from day one. Everything shipped through standardized CI/CD with SLAs and real observability, so teams could move fast without owning the dangerous parts themselves.

System design

Access
Self-service portalSSO · Okta / OAuth2Operator dashboard
Orchestration
Multi-model routerMCP toolingRust agent runtimes
Models
OpenAIAnthropicOpen-weights
Platform
Kubernetes (EKS)GitHub Actions CI/CDPrometheus · Grafana · OTel
Cloud
AWS

What I built

Outcomes

−40%
Model deployment time
−50%
Engineer onboarding time
−60%
CI/CD cycle time
+15%
System uptime
−40%
Mean time to recovery

Stack

Kubernetes (EKS)AWSRustPythonGitHub ActionsPrometheus/GrafanaOpenTelemetry