Services

I build AI products, cloud platforms, and engineering systems.

I work with founders and engineering teams to build production AI software, create the AWS platforms behind it, improve how teams deliver it, and solve the technical problems that slow progress.

Discuss your project

How this works

These are hands-on engineering engagements. I work directly with the product, codebase, architecture, infrastructure, and engineers rather than stopping at high-level recommendations.

The outcome is concrete progress: working software, stronger infrastructure, clearer technical decisions, or a delivery system the team can continue using.

Services

01

AI Products & Agents

Production AI agents, copilots, RAG systems, and workflow automation built for reliability, security, and real-world use.

I build the software around the model: interfaces, retrieval, permissions, validation, observability, workflow controls, and the application code required to make the system useful in production.

What this covers

  • Tool-using agents with permission gates and audit trails
  • Context-aware copilots and structured assistants
  • RAG pipelines: ingestion, retrieval, reranking, and grounding
  • Workflow automation with approvals and escalation
  • Security, observability, evaluation, and production hardening

Good fit: Founders and engineering teams building an AI product or moving a prototype towards production.

02

Cloud Platforms for AI

AWS platforms that power production AI—from infrastructure and CI/CD to observability, security, and scalable cloud architecture.

I design and build the AWS foundation around the product, covering infrastructure, deployment, security, observability, reliability, and the operational paths required to run it confidently.

What this covers

  • AWS architecture: accounts, networking, compute, and storage
  • Containers and serverless systems: ECS, Lambda, and autoscaling
  • Infrastructure as code: Terraform, AWS CDK, and CloudFormation
  • CI/CD, environment management, and release engineering
  • Observability, security, reliability, and cost control

Good fit: Teams taking an AI product or application from prototype to a production AWS environment.

03

AI-Native Engineering

Modern software delivery with coding agents, specification-driven development, developer tooling, and engineering workflows that scale.

I design specifications, project context, tests, tooling, Git workflows, and guardrails that let coding agents accelerate delivery without weakening review, ownership, or architectural control.

What this covers

  • Specification-driven development workflows
  • Coding-agent adoption: Claude Code, Codex, and AWS Kiro
  • Project steering, curated context, and engineering guardrails
  • Testing, CI/CD, and quality gates for agent-assisted code
  • Git workflows and change sizes designed for meaningful review

Good fit: Engineering teams adopting coding agents that want more speed without losing quality or architectural control.

04

Technical Leadership

Hands-on engineering leadership for ambitious teams—designing architecture, solving difficult technical problems, and shipping production software.

I work directly with founders and engineers to set technical direction, make architecture decisions, investigate difficult problems, and move important software towards production.

What this covers

  • Technical direction and architecture decisions
  • AI systems and cloud platform architecture
  • Difficult production problems and root-cause analysis
  • Delivery leadership: sequencing, ownership, and risk
  • Code review, mentoring, and practical engineering standards

Good fit: Founders and engineering teams that need senior technical judgement embedded directly in the work.

How I work

I work close to the system and the people building it. Depending on the engagement, that usually includes:

  • Understanding the current codebase, architecture, and operational constraints
  • Turning unclear requirements into small, testable delivery steps
  • Building prototypes to resolve uncertainty before committing to a larger design
  • Writing and reviewing production code, infrastructure, and tests
  • Making system behaviour visible through logs, metrics, traces, and evaluations
  • Leaving behind clear decisions, maintainable software, and a team able to continue independently

Choosing where to start

Most engagements start in one of four places:

  • A product or agent to build — start with AI Products & Agents.
  • Infrastructure that needs to hold up in production — start with Cloud Platforms for AI.
  • A team adopting coding agents — start with AI-Native Engineering for a delivery model that combines agent speed with engineering discipline.
  • A difficult technical problem or a team that needs direction — start with Technical Leadership for senior engineering judgement embedded in the work.

The boundaries are intentionally flexible. Most engagements draw on more than one area once the product, platform, and delivery constraints become clear.

Bring me the difficult part.

Tell me what you're building, what already exists, and where progress is slowing. I'll suggest a practical way to approach the work.

Get in touch