Perimattic
ML and MLOps

MLOps Consulting and ML Frameworks

The frameworks we train models with and the tooling that takes them to production: versioned, monitored and retrainable. Our defect detection proof of concept, built with Python, PyTorch and OpenCV, made the right call on all 51 evaluation bottles.

What this stack covers
  • Deep learning with PyTorch and TensorFlow
  • Computer vision with OpenCV and YOLO
  • Classic ML with scikit-learn and XGBoost
  • Experiment tracking with MLflow and Weights & Biases
  • Training on GPUs, Vertex AI, Azure ML and SageMaker
Overview

What is MLOps, and why does it matter?

MLOps is the practice of taking machine learning models from a notebook to production and keeping them working there: versioning data and models, automating training and deployment, and monitoring accuracy so drift is caught early. Without it, a model that scored well in testing quietly degrades once real data changes.

Our ML work is mostly computer vision for manufacturing and healthcare. The framework matters less than the discipline around it: held-out evaluation data, honest accuracy figures with confidence bounds, and a repeatable path from a new model version to production.

Last updated by the Perimattic engineering team.

Analytics dashboard on a screen showing usage charts
51 of 51
correct decisions in a defect detection proof of concept
24 of 24
faulty bottles caught, none wrongly rejected
60%
faster DICOM scan analysis in healthcare
The Stack

Which ML frameworks and MLOps tools do we use?

Each tool is marked honestly: named in a published client project, or one we work with but have no published project for yet.

PyTorch

Used in client projects

Trained the cap locator and seam check models in the bottle-cap defect detection proof of concept. Our default for new deep learning work because of its research ecosystem and pretrained models.

TensorFlow

We work with it

We work in TensorFlow when a client already has models or tooling built on it, or needs TensorFlow Lite for on-device inference.

Computer vision libraries

Used in client projects

OpenCV handles image and frame processing in the bottle-cap inspection and the lung-disease detection system. We use YOLO-family detectors for object detection and Tesseract for OCR where it fits.

OpenCVYOLOTesseract

NumPy and classic ML

Used in client projects

NumPy sits under the bottle-cap pipeline. For tabular problems such as forecasting, scoring and classification, gradient-boosted models in XGBoost or LightGBM often beat deep learning at a fraction of the cost.

scikit-learnXGBoostLightGBM

Speech and NLP libraries

We work with it

spaCy for entity extraction and text pipelines, and Whisper for speech-to-text, when a task does not need a full large language model.

spaCyWhisper

MLflow

We work with it

Experiment tracking and a model registry, so every production model can be traced back to its data, code and metrics.

Weights & Biases

We work with it

An alternative to MLflow for teams that want hosted experiment tracking and richer visual comparisons between training runs.

W&B

Training infrastructure

We work with it

GPU training on the cloud the client already uses. For SageMaker work, see our AWS AI/ML services.

CUDARayVertex AIAzure MLSageMaker
What We Build

What do we build with this stack?

Six kinds of ML work make up most projects. Most start with a proof of concept against agreed accuracy targets.

Visual inspection

Defect detection on production lines, as in the bottle-cap proof of concept that caught all 24 faulty bottles.

Medical imaging

Second-opinion models for scans, integrated with PACS, as in the lung-disease detection system.

Forecasting and scoring

Demand forecasts, risk scores and classifiers on tabular data, usually with classic ML.

Training data pipelines

Frame sampling, labelling and dataset versioning, the work behind every reliable model.

Model deployment

Turning trained models into versioned, containerised APIs with rollback.

Monitoring and retraining

Accuracy and drift monitoring with a retraining path, so models keep up with real data.

Trade-offs

ML choices we make most often

Most of the cost and risk in ML is decided before training starts. These are the calls we make on most projects.

  • PyTorch or TensorFlow?

    PyTorch for new work; TensorFlow when your existing models or devices use it

    PyTorch has the larger pool of current pretrained models. Rewriting working TensorFlow code rarely pays back.

  • Deep learning or classic ML?

    Classic ML for tabular data; deep learning for images, audio and text

    Gradient-boosted trees are cheaper to train, explain and run on structured data.

  • Custom model or a hosted AI API?

    A hosted API when it meets the accuracy target; a custom model when it does not

    We test the cheapest option first against your own data before training anything.

  • MLflow or Weights & Biases?

    MLflow when you want to self-host; Weights & Biases for a hosted service

    Both track experiments well. The deciding factor is where your data is allowed to go.

Proof

Which ML systems have we shipped?

These case studies list PyTorch, OpenCV or NumPy in their published tech stack.

01

Honest accuracy

We publish results with sample sizes and confidence bounds, and say what is not yet proven.

02

Built for the line, not the lab

Models are designed around real camera positions, frame rates and integration with existing systems.

03

Production from the start

Containerised models, versioned data and monitoring are part of the build, not an afterthought.

How We Deliver

How do we deliver ML and MLOps projects?

Five stages, from scoping call to release. Every engagement is priced before the work starts.

  1. 1

    Scoping call

    Goals, constraints and the existing stack, with a written scope and fixed price before any build.

  2. 2

    Architecture

    Stack choices written down with the trade-offs, reviewed with your team before code starts.

  3. 3

    Build in sprints

    Short sprints with a working demo at the end of each, on a staging environment you can use.

  4. 4

    Release

    CI/CD, automated tests and monitoring in place before production traffic arrives.

  5. 5

    Handover or support

    Documented code and runbooks for your team, or ongoing support and maintenance from ours.

On ML projects we agree accuracy targets and a held-out evaluation set before training, and report results with confidence bounds rather than a single headline number.

FAQ

ML and MLOps: common questions

What is the difference between MLOps and DevOps?

DevOps automates how code is built and shipped. MLOps adds the parts specific to models: versioning data, tracking experiments, evaluating accuracy before release and monitoring for drift afterwards.

Which ML framework do you use?

PyTorch for most new deep learning work, OpenCV for image processing, and scikit-learn or XGBoost for tabular data. We work in TensorFlow when a client's existing models use it.

How do you prove a model works?

We test on data the model never saw in training and report results with confidence bounds. The bottle-cap proof of concept, for example, reports at least 94.3% accuracy at 95% confidence, not just 51 of 51.

Can you put our existing models into production?

Yes. We wrap them as versioned, containerised APIs, add monitoring for accuracy and drift, and set up a path to retrain and redeploy.

Do we need MLflow or Weights & Biases?

Once more than one person trains models, yes. Experiment tracking is how you know which data and settings produced the model in production.

Get Started

Have a model to build or put into production?

Tell us the problem, the data you have and the accuracy you need. You will get an honest view of feasibility and, if it fits, a fixed-price proof of concept.

  • 30-minute call about your project and current stack
  • Honest read on whether this stack fits your project
  • Written scope and fixed price before any build