Architect@IBM

AI/ML | Cloud | Integration | Automation

About Me

I’m an experienced technical architect and engineer in the IBM Technology, Client Engineering Team. I lead multidisciplinary engineering teams in the design and build of next generation data & AI, automation, integration and hybrid cloud technologies. I sit on the British Standards Institute (BSI) ART/1 Artificial Intelligence Committee, a mirror committee for the international ISO/IEC JTC 1/SC 42 and European CEN/JTC 21 committees, contributing to the development of AI standards as a national expert. I also sit on the Ecosystems Architecture and AI Working Groups at The Open Group contributing to standards for professional practice. I have been a member of the University of London Data Science MSc academic tutor team teaching AI and Machine Learning. I am an IBM Certified Architect, IBM Certified AI Engineer, GCP Professional Cloud Architect, GCP Professional Machine Learning Engineer and certified in Data Science and Machine Learning (HarvardX). I am a Certified Information Systems Security Practitioner (CISSP, ISC2) and certified in Red Hat Openshift. I graduated with First Class honours in Computer Science and hold a Masters degree from Cambridge University. I post here mostly about architectural patterns and engineering exploits that I am able to talk about.

SVD for constructing semantic knowledge graphs, semantic retrieval and reasoning

Singular Value Decomposion (SVD) is a well known method for latent semantic analysis. When applied to BERT contextual embeddings SVD produces three components: U, Σ, and V. The eigenvectors in V represent distinct semantic patterns - each one captures a different aspect of meaning in the text. The eigenvalues in Σ tell us how significant each pattern is, effectively showing us what is semantically important and where the semantic “holes” are - the gaps in meaning that separate different semantic clusters. This elegant mathematical decomposition reveals the fundamental building blocks of meaning in text, creating a natural hierarchy of semantic patterns that can be analyzed through linear algebra and externalised a semantic knowledge graph.

Operating AI at Scale with OpenShiftAI, KubeFlow Pipelines and watsonx

Operating AI across different clouds and execution engines becomes complex and difficult to maintain with cloud native tools as the number of different integrations between systems proliferates at scale. OpenShiftAI provides a cohesive hybrid, multi-cloud AI platform that enables enterprises to separate concerns between pipeline orchestration and workload execution reducing complexity in the data and governance subdomains and enabling enterprises to operate AI at scale.

Tool-Agents with the watsonx LangChain BaseChatModel

The watsonx.ai BaseChatModel supports integration with LangChain for building LangChain Tool-Agents. The following code demonstrates use of the LangChain watsonx BaseChatModel to construct a Tool-Agent. The application logic follows: (1) a call to the language model to determine which tools to invoke; (2) the programmatic invocation of the selected tools (3) a final call to the watsonx language model with the response from the tools.

See all