Systems

Full-stack ML systems, documented end-to-end.

Each system is paired with two verification paths: live docs (what it does) and an evidence memo (what it proves, how to verify, risks & mitigations). This structure is optimised for technical screening and ATS parsing.

CI/CD for ML Inference Scaling Feature Engineering Backtesting RAG / LLMOps

Signal → Systems → Proof Ledger

NeuroGrid Fault Risk Scoring Platform

Medium-voltage fault risk inference with CI-minded training flow, artefact versioning, and live API serving.

End-to-End ML Model Serving CI Training Versioned Artefacts

Open system Evidence memo Proof anchor API docs

Forecast Studio (Time-Series Production Pipeline)

Forecasting as a system: feature pipelines, backtesting harness, and deployment-ready outputs for planning workflows.

Time-Series Backtesting MLOps Monitoring-ready Outputs

Open system Evidence memo Proof anchor Source

RAG Knowledge Copilot (LLMOps Reliability)

Retrieval tracing, grounded drafting, and guardrails — designed to evidence production-minded LLMOps.

RAG LLMOps Evaluation Harness Guardrails Citation Discipline

Open system Evidence memo Proof anchor Source (site repo)