Lead AI Engineer · London
Abd Bastola.
Fetching the engine
Building the campus
The interactive campus is unavailable here
This experience needs WebGL and the 3D module. Your browser, graphics driver or connection may have interrupted it.
Nothing has been lost: this page, its URL and its content are intact. Everything the site contains — the CV, every article and case study, the repositories and the contact options — is ordinary readable HTML inside the world's own panels.
Lead AI Engineer · London
I build AI systems people can rely on.
Production-grade agents, RAG and GraphRAG platforms for enterprise teams — with the unglamorous parts designed in: evaluation, guardrails, observability and clear limits.
Currently Building and delivering enterprise AI systems at AWTG in London — including the KAI platform.
Three engagements, each documented end to end: the problem, my contribution, the architecture and the outcome.
An enterprise AI assistant that helps teams find, understand and use trusted organisational knowledge.
Led delivery of a GraphRAG and document-intelligence platform that turns complex, unstructured learning content into connected, searchable knowledge.
An AI-driven approach to reduce RAN energy consumption while maintaining service quality.
Notes on building production-ready AI agents, RAG systems, evaluation and enterprise AI delivery.
Prompt injection, data leakage, tool abuse, model supply chains and token-burning denial of service. A practical mental model for thinking about AI security the way you already think about the rest of your architecture.
OpenAI's Astra launch is being framed as the start of something huge. A practical read on what the coverage actually signals about real-time multimodal and agentic models — transparency, control, safety, evaluation, cost and governance.
Voice agents are suddenly ready for the enterprise — which means teams are choosing between cascaded pipelines, all-in-one platforms and direct provider stacks. A practical look at the latency trade-offs, the compliance realities and the business impact that should drive the decision.
Business problem definition, data readiness, risk classification, model selection, MVP scope and measurable success criteria — the six questions that prevent model-first projects from becoming expensive regrets.
Real repositories — agents, GraphRAG experiments, reinforcement learning for RAN and automation tooling.
Conduct-style change assurance layer with LangGraph orchestration and policy governance.
View repositoryProduction-shaped ACL GraphRAG interview demo (NTT DATA Option 1).
View repositoryAI reference-based ranking video generation platform — Tech Europe hackathon build.
View repositoryAG-UI hackathon project — an AI study companion (edumate).
View repositoryDQN agent that switches 5G cells on and off, using energy efficiency as the reward signal.
View repositoryPPO (actor-critic) reinforcement-learning agent for Advanced Sleep Mode in RAN.
View repositoryA concise daily briefing on enterprise AI agents, RAG, evaluation, security and the ideas worth understanding before they become industry noise.
A confirmation tab will open — finish there, then check your inbox. One concise daily briefing, no spam, unsubscribe anytime.
Designing an agent, fixing a RAG pipeline, planning evaluation and governance, or hiring — send a message and I’ll reply personally.
