Skip to content
VDAI with VD

Service

MLOps

Pipelines, monitoring, versioning and cloud deployment for models in the wild.

Talk to me about this

What I build

The operational layer that keeps models useful after launch: pipelines that rebuild datasets and models on demand, registries that record what is running where, deployments with rollback, and monitoring that catches drift before users do.

How I work

I treat a model like any other release artefact. It has a version, a test suite (the evaluation set), a deployment pipeline and a dashboard. Cost is a first-class metric, tracked per request from day one.

When to call me

You have a model in production that nobody can confidently redeploy, or you are about to launch one and want it to survive its first month.

What you get

  • Reproducible training and data pipelines
  • Model and dataset versioning with a registry
  • Deployment on AWS or your cloud, containerised, with rollback
  • Monitoring for drift, latency, cost and quality

Selected work

Case studies for this service

hypREspace

Measured

hypREspace: Cutting Token Costs 90% While Raising Tool-Calling Accuracy to 95%

Dynamic prompt injection, a gold evaluation set and Amazon Nova fine-tuning cut a live agent's token spend by 90% and lifted tool-calling accuracy from 75.8% to 95%.

Measured outcomes

Measured with before-and-after per-query token counts and tool-call accuracy scored against the gold evaluation set.

90%

Token cost reduction, measured per query

75.8% to 95%

Tool-calling accuracy on the gold eval set

Read case study

Self-Built Project

Demonstrated

Document Extraction Pipeline: Scaling AI Workloads with FastAPI and Celery

An async-first extraction service: FastAPI accepts uploads, Celery workers run OCR and LLM extraction, and typed schemas turn invoices, legal documents and ESG reports into JSON.

Demonstrated capabilities

These are implemented capabilities and supported schemas; no comparative speed or accuracy benchmark is claimed.

Async

Queued worker processing keeps uploads responsive

Typed JSON

Schema-validated output for supported templates

Read case study

Related work

Related projects

Document Extraction Pipeline

Turn Documents into Structured Data with AI

Self-Built ProjectDemonstrated

A production-ready FastAPI service that extracts structured data from PDFs and images using OCR and LLM technology. Features async processing, JWT authentication, and support for multiple document types including invoices, legal documents, and ESG reports.

FastAPICeleryPostgreSQL

Questions I get asked

Do you work with our existing cloud?

Yes. Most of my deployments run on AWS (ECS, Lambda, Bedrock, S3) but the patterns apply to GCP and Azure, and to on-premise Docker hosts when data cannot leave the building.

What do you monitor?

Input drift, output quality against a sampled gold set, latency percentiles, error rates and cost per request. Alerts go where your team already looks.

How is this different from DevOps?

It is DevOps plus the parts models add. Data versioning, evaluation gates in CI, and the ability to retrain or roll back a model without redeploying the product.

Have a problem that looks like this?

Tell me about it. I reply within one working day with a first take and no sales pitch.

Book a callSend a message