Looking for a senior ML engineer

I’m looking for a senior ML engineer to conduct an independent technical audit of the completed Stage 5 work for ESGIQ, a carbon-project risk and underwriting-support platform. The current system is a time-aware, multi-model proxy benchmark covering project delivery, issuance, delay, integrity and developer risk. The handover includes the modelling dataset, feature store, trained model bundle, Python code, target definitions, temporal validation, calibration, leakage audits, explainability outputs, prediction API, tests, manifests and a GitHub-ready production repository. I am not asking you to rebuild or modify the model initially. I need you to independently assess whether the work is reproducible, leakage-safe, technically defensible and ready for the next validation phases. The review would need to examine: * Time-based train, validation and test splits. * Separation of repeated project snapshots and developers. * Target and proxy-label validity. * Potential direct, indirect and temporal leakage. * Credibility of the reported performance and calibration. * Unseen-project, unseen-developer and future-time validation. * Consistency between the technical handover and production repository. * Whether the main results can be reproduced from the supplied package. The final output should be a written audit with a severity-ranked findings register, required corrections and an overall conclusion: accept, accept subject to corrections, material rework required or not reproducible. Before I send the two ZIP packages, could you confirm whether you have personally audited time-aware tabular ML models, grouped project/developer validation, probability calibration and data leakage? If so, could you briefly describe one relevant example and indicate whether you would offer this as a fixed-fee diagnostic?