I take on a small number of consulting engagements each year. I like this work. It keeps me inside real production constraints, which is where the useful patterns come from. Every engagement feeds the writing on this site, and the writing feeds the engagements.

Services

  • Bedrock and LLM platform architecture. Cost-aware foundation for production LLM workloads. Model routing, inference profiling, guardrail design, multi-region failover. You ship features, not infrastructure.
  • LLM cost optimization. Most teams overpay 60-90% on Bedrock Knowledge Base, OpenSearch Serverless, and provisioned throughput because the pricing model is non-obvious. I find the waste, restructure the stack, and hand you the cost dashboard.
  • Agentic pipeline design. Moving from chat to agents. Tool-use architecture, agent loop design, human-in-the-loop checkpoints, tracing and observability for non-deterministic workflows.
  • S3 Vectors and RAG architecture. Native S3 vector search, chunking strategy, embedding model selection, retrieval evaluation. Skip the “just add a vector DB” reflex.

How I work

Project-based. You have a specific feature, pipeline, or migration. I build it alongside your team and transfer ownership with documentation.

Hourly advisory. You have good engineers and want a second pair of eyes on architecture decisions. We talk when you need to.

Interim AI platform lead. Your team is growing past the prototype phase and needs someone who has shipped LLM workloads to production before. I step in for a fixed stretch, set direction, and help hire or promote the permanent lead.

Who this is for

Teams that already have engineering talent but need someone who has done the specific thing before. You are past the “can we call Bedrock from a notebook” stage and into the “how do we make this safe, cheap, and observable at scale” stage.

Credentials

  • Senior cloud platform engineer, 7+ years on AWS.
  • AWS Certified Solutions Architect, Associate.
  • AWS Community Builder since 2022.
  • Built and shipped LLM workloads on Bedrock since preview.
  • Cut Bedrock Knowledge Base costs by 90% migrating from OpenSearch Serverless to Aurora Serverless v2 with pgvector. Wrote about it.
  • Rotterdam chapter organizer for Claude Community NL.

Reach out

No pitch deck. No discovery form. A short message on LinkedIn about what you are trying to ship and what the bottleneck looks like. We take it from there.

For work, consulting, or speaking inquiries, LinkedIn is the fastest path to a reply.