Skip to content
Andrew Kaiserauer

Manager, Platform Engineering, Deloitte · Detroit metro area · Open to remote

Engineering and platform leader who builds the systems other engineers build on

I run a 33-person Platform Engineering org at Deloitte and build AI infrastructure hands-on, from multi-tenant Kubernetes platforms to LLM inference systems.

View workGet in touch
LinkedInGitHubDownload resume

About

I build and lead platform engineering organizations. Today I run a 33-person Platform Engineering org at Deloitte, four squads with dedicated tech leads, where I treat the internal developer platform as a product serving thousands of engineers across the US Member Firm.

Outside work I build extensively in TypeScript and Python, including a growing body of AI infrastructure and agentic-system projects: LLM inference serving and performance engineering, enterprise agentic workflows, and a published design system.

I'm targeting senior roles in engineering management, platform engineering, AI forward-deployed and inference platform, and cloud and solutions architecture.

Experience

  1. 2021 – Present

    Manager, Platform Engineering · Deloitte

    • Built the Platform Engineering organization from scratch: four squads with dedicated tech leads, serving thousands of engineers across the US Member Firm.
    • Architected a multi-tenant Amazon EKS platform running 40+ microservices at roughly 99.95% uptime.
    • Standardized CI/CD and container delivery across 15 teams with golden images and GitOps (ArgoCD) — deployments went from hours to minutes and incidents fell about 30%.
    • Led adoption of Backstage for 50+ services, cutting onboarding from weeks to days.
    • Designed an internal platform product built on SCIM provisioning, a shared authorization service, and a policy-enforcement engine with SOX-ready audit trails.
    • Led the enterprise rollout of GitHub Copilot and agentic development workflows.

  2. 2018 – 2020

    Senior Infrastructure Architect · GE Aviation

    • Delivered 25+ cloud migrations and new builds, generating about $1.9M in infrastructure cost savings.
    • Built self-service AWS observability and native CI/CD that cut deployment time from an hour to two minutes.

  3. 2015 – 2018

    Cloud Automation & Enterprise Application Engineering · GE Digital / GE Healthcare

    • Built cloud automation bots and cookbooks, cost-optimization tooling, and led Agile delivery.

Projects

  • AI Infrastructure

    inference-platform

    A platform for LLM inference serving: GPU scheduling, high-throughput serving with vLLM and KServe, and inference-aware autoscaling with KEDA on Kubernetes, with observability and cost/SLO discipline built in.

    • Python
    • Kubernetes
    • KServe
    • KEDA
    • Envoy AI Gateway
    View site for inference-platform

  • AI Infrastructure

    llm-inference-performance

    Inference performance engineering end to end: a device-aware benchmark harness (p50/p95 latency, tokens/sec, peak memory), measured KV-cache, batching, and int8-quantization optimizations, tensor-parallel serving, and a custom fused-RMSNorm CUDA kernel.

    • Python
    • PyTorch
    • CUDA
    Coming soon

  • AI Infrastructure

    ops-triage-agent

    An enterprise agentic system that triages an IT/Ops queue end to end: retrieves context, drafts grounded responses, and takes guarded actions behind human-approval gates, with every release gated by an evaluation harness.

    • Python
    • FastAPI
    • React
    • TypeScript
    • MCP
    Coming soon

  • micro-ceo

    An AI orchestrator that simulates a company hierarchy of LLM agents (CTO, VP Eng, engineers) that communicate, produce artifacts, and escalate decisions to the user.

    • TypeScript
    • Electron
    • LLM SDKs
    Coming soon

  • design-system

    A published React + Tailwind v4 component library (@kornorg/design-system): neutral zinc surfaces, indigo accent, light and dark mode, distributed as an installable npm package.

    • TypeScript
    • React
    • Tailwind
    • tsup
    View on npm for design-system

  • deCuisine

    A full meal-planning and grocery SaaS: recipe discovery, weekly planner, auto-generated grocery lists, grocery-store integration, and subscription billing.

    • Next.js
    • Prisma
    • Postgres
    • Stripe
    Live site for deCuisine

Also built: graham-crackers (Graham-style value-investing analysis tool), audiobook-generator (local TTS EPUB-to-M4B pipeline), macos-media-scanner (Photos-library cleanup CLI).

Skills

Engineering Leadership

  • Building & scaling platform orgs
  • People management (33 reports)
  • Product & roadmap ownership
  • Agile / SAFe
  • Executive communication

Cloud & Platform

  • Kubernetes / EKS
  • GitOps (ArgoCD)
  • Terraform / IaC
  • Docker
  • AWS
  • Prometheus / Grafana / Loki
  • SRE / SLOs
  • CI/CD
  • GitHub Actions

Identity & Security

  • IAM & authorization design
  • SCIM
  • OAuth / OIDC
  • Policy enforcement & governance

Software Engineering

  • Python
  • FastAPI
  • Microservices
  • TypeScript
  • React
  • Next.js
  • Tailwind
  • Drizzle / Postgres

AI Engineering

  • LLM applications & agentic systems
  • LLM inference serving & performance
  • Evaluation harnesses
  • MCP
  • Enterprise AI enablement (Copilot rollout)

Contact

Interested in working together?

I'm open to conversations about senior engineering leadership, platform and developer experience, and AI infrastructure roles. The fastest way to reach me is email.

ajkaiserauer@gmail.comLinkedInGitHub