Neil Miles, Founder, Inawisdom
The Inawisdom DevOps practice is a core capability, responsible for taking Machine Learning (ML) and data driven projects and embedding them in businesses processes systems to deliver value. Once embedded, we maintain these to ensure the value continues long term and drives on-going business value.
The practice is responsible for architecting serverless solutions, building applications and integration with enterprise architectures. The projects the DevOps practice undertakes cover the full solution life-cycle: from prototype, using AWS ML services to full production deployments, using DevOps and following AWS best practices.
DevOps is essential to the full life cycle capability that we offer to our customers; it is a process and culture that allows us to quickly deliver value by taking ML and delivering it into the heart of a customer’s business. In addition, we also use DevOps in-build prototypes to showcase the future potential that ML could have as a differentiator or disruptor in their market or industry
Inawisdom uses a cloud native and serverless approach to the solutions our engineering’s create. This involves using Lambda, API Gateway and StepFunctions as critical elements of the architectures and micro services that we develop. These services also provide the foundation for creating ML Ops processed that support the operational of machine learning model at scale. Lastly we pride ourselves on educating clients on the use of serverless technology including how to deploy, debug, optimise and observe the operation on Lambda function in production workloads.
Inawisdom’s Rapid Analytics and Machine Learning Platform (RAMP) solution helps organizations quickly ingest and analyse vast amounts of data from different sources to gain significant advantages from machine learning and AI services. Find out more about our platform
Learn about RAMP on AWS at the AWS Solutions Space
Machine Learning and Automated Model Retraining with SageMaker
Building ML base solutions taking data science outputs e.g. Jupyter notebooks, trained model and AWS ML Services, and through DevOps practices quickly enable business validation of the project hypothesis and showcasing the capabilities of ML.
Productionising ML solutions, ensuring they are highly secure, reliable, performant and cost efficient.
The deployment of ML models and associated components using build tools and Infrastructure as Code to provide consistency and traceability.
The ongoing automated monitoring and alerting is built into solutions to ensure high availability and that target response times are met.
Providing KPI’s to judge business impact and service levels are understood, measured and achieved
Uniquely integrating tools such as AWS X-Ray to provide complete observability of ML in production to identify issues, bottlenecks or potential optimisations.
One the most critical aspects that our DevOps practice leads on is retraining of models and using multiple deployment options (depending on the customer need) when updating them.
Use of Continuous Integration and Continuous Deployment pipelines that take new data, cleans and transforms the data, runs incremental training of ML models, verifies their accuracy and then deploys them into production.
See how we have helped our customers achieve success utilising our DevOps capabilities:
View more of our customer case studies.
Check out some of our most popular DevOps blogs:
