Enterprise AI & GenAI Solution Architect | LLM Multi-Agent Systems | Chief Technology Officer
Psychology-Informed Governance | Evidence-Led Evaluation
I design and govern enterprise AI systems where decisions must remain explainable, testable and accountable. I currently serve as Chief Technology Officer and target Enterprise AI and GenAI Solution Architect roles.
My distinctive specialisation is the architecture, governance and evaluation of LLM multi-agent systems: how topology, role design, authority, information flow, dissent, verification and human oversight affect decision quality. My foundation includes eighteen years at Enel Group across enterprise technology, electricity-distribution systems, transformation, programme delivery and capability development.
Formal training in Psychological Sciences gives me a complementary, non-anthropomorphic lens on authority bias, conformity, groupthink, social loafing and confidence dominance. I do not assume that LLM agents possess human motives. I translate these concepts into observable failure hypotheses, structural controls and evaluation designs.
Current proposed, testable designs cover:
- separating procedural from epistemic authority;
- structured dissent, falsifiable objections, blind review and external verification;
- role permutation, agent ablation and adversarial-leader testing;
- compute-equivalent single-agent baselines;
- measures of task correctness, dissent robustness, cascading error, traceability and cost.
This work currently supports conceptual architecture and evaluation design. Proposed controls and measures remain explicitly labelled as such until they have been implemented and benchmarked.
- Architecture: governed integration, model routing, retrieval, APIs, event-driven data flows and human oversight.
- Agentic governance: roles, permissions, explicit state, structured dissent, external evidence, traceability and fail-closed controls.
- Evaluation: explicit assumptions, predefined success and failure criteria, telemetry and validation against observed results.
- Engineering: Python, TypeScript, FastAPI, LangGraph, PostgreSQL, Docker, GitHub Actions, automated testing and observability.
As CTO, I am responsible for technology direction, engineering governance, delivery quality, organisational design, supplier qualification and technical input to proposals and contracts. I lead five direct reports and coordinate fifteen contributors functionally. I also authored my company's guidelines for AI-assisted software development, translating recent academic literature into controls for requirements, architecture, implementation, testing, traceability, validation and human accountability.
A deployed reference PoC for a bounded, governed agent workflow with sovereignty-aware model routing, human approval, auditable decision lineage and execution telemetry. Live reference demonstration.
Scope boundary: this is a fixed, typed workflow with governed model invocation. It is not an autonomous general-purpose multi-agent runtime, a restart-safe distributed executor or a multi-tenant production platform.
A runnable architecture PoC for a policy-governed AI-assisted software factory core, using contract-first schemas, explicit state transitions, PostgreSQL leasing, data-residency and cost-aware routing, and fail-closed controls.
Scope boundary: this is an inspectable governed core and architecture PoC, not a complete production software factory.
An open-source ML portfolio application connecting electricity-distribution domain knowledge with temporal validation, reproducible training and evaluation, MLflow artefacts, Docker packaging and GitHub automation.
Scope boundary: the separate live FastAPI demonstration endpoint is rule-based; it is not an Enel production system or evidence of continuous trained-model serving.
Question → literature review → explicit assumptions → success and failure criteria → instrumentation → validation. I separate evidence, inference and hypothesis, then revise architectural decisions against observed results and documented limitations.
- MSc Artificial Intelligence, University of Liverpool — in progress.
- PGCert Data Science and Artificial Intelligence, University of Liverpool — academic requirements completed; formal award pending.
- Master's Degree in Management and Innovation.
- Bachelor's Degree in Psychological Sciences and Techniques.
Neuromorphic Inference Lab is an independent open-source initiative. I define architectures and specifications, direct AI-assisted implementation, review code and tests, and remain accountable for validation, limitations and deployment decisions. The repositories demonstrate inspectable patterns and bounded PoCs; they are not presented as customer production platforms, validated research frameworks or evidence of years operating autonomous multi-agent runtimes at scale.