Governed AI platform infrastructure for regulated environments
I build the production platforms that run LLMs and agents where audit, security, and reliability are not optional - for banks, fintechs, and high-stakes operators. Multi-account AWS, governed model access, and the controls a regulated environment demands.
See What I Build Get in TouchWhat I Build
I focus on the infrastructure that runs AI in production for organizations where governance and reliability are first-class requirements - not the demo, the deployment.
AI & LLM Platform Engineering
Governed platforms for running LLMs and agents in production: AWS Bedrock and LiteLLM gateways, multi-account architecture, access control, observability, and cost governance. The infrastructure layer that turns an AI experiment into something a regulated org can actually run.
AgentOps & Production AI Reliability
Operating agentic systems safely once they are live: health monitoring, human-gated actions, and audit trails. The discipline of running AI in production rather than prototyping it. (See Tendwell, below.)
Core DevOps & Cloud Engineering
The full foundation, in any environment: AWS and Azure architecture, Kubernetes, CI/CD, Infrastructure as Code with Terraform and Ansible, and production incident response. Six-plus years across banking, iGaming, and fintech, applying security and audit rigor wherever it is useful - regulated environment or not.
Beyond AI platforms, I take on core DevOps and cloud engineering - cluster design, IaC, CI/CD, migrations, and troubleshooting. If you need infrastructure built or fixed, it is in scope.
Tools I've Built
I build the tools I wish existed for this work.
Tendwell
Self-hostable, local-first AgentOps for production health. It observes metrics and runbooks, reasons with a local LLM, and explains what it finds - with human-gated, hash-chained-audited actions. Built for security-conscious and regulated teams.
Explore TendwellTerraback
Reverse engineer your cloud infrastructure into Terraform code. Convert existing AWS, Azure, and GCP resources into clean, maintainable Terraform code with a single command.
Visit Terraback.ioLatest from the Blog
Operating Agentic Systems in Production: Lessons from Building Tendwell
The hard part is not the model, it is the guardrails around it - the propose/approve/execute separation, local-first as a hard default, and audit as a feature.
The four-hour clock starts before you understand the incident: notes on DORA Article 17 in practice
Field notes on DORA Article 17 in practice - why incident classification is harder than the regulation makes it look, and why the tooling you bring in is itself a compliance surface.
Building AI platforms where reliability and compliance matter?
If you are running - or planning to run - AI in a regulated or high-stakes environment, let's talk about the infrastructure underneath it.
Get in Touch