We are seeking an ML Engineer Architect & Lead to pioneer the architectural design, development, and scaling of our enterprise machine learning and advanced analytics systems on Google Cloud Platform (GCP). In this hybrid technical leadership role, you will lead the implementation of complex predictive modeling, anomaly detection, graph analytics, and semantic search capabilities. You will be responsible for translating sophisticated mathematical and statistical techniques into production-grade pipelines, establishing blueprint patterns for model training, deployment, and explain ability using the Vertex AI ecosystem.
Key Responsibilities
● Architectural Leadership: Own the end-to-end Machine Learning architecture on GCP. Define blueprint patterns for scalable model training, continuous deployment, evaluation, and serving infrastructure.
● Advanced Predictive & Anomaly Modeling: Design, build, and optimize high-performance predictive models using XGBoost alongside robust anomaly and fraud detection mechanisms using Isolation Forests (IsoForest).
● Distributed Scale Analytics: Architect and execute large-scale, distributed frequent pattern mining and association rule learning pipelines utilizing PySpark FPGrowth.
● Graph & Network Architecture: Build complex network analysis frameworks, relationship graphs, and community detection systems using NetworkX and python-louvain.
● Vector & Semantic Search: Implement production-grade semantic search, similarity matching, and retrieval architectures using text embeddings integrated with BigQuery Vector Search.
● Orchestration & Automation: Build, test, and maintain fully automated ML lifecycles (CI/CD/CT) utilizing Vertex AI Training and Vertex AI Pipelines.
● Model Governance & Explainability: Implement strict model interpretability and feature attribution compliance frameworks across all production workflows using SHAP (SHapley Additive exPlanations).
Required Technical Skills
● Core ML Frameworks: Expert-level mastery of Python and standard data science toolkits, with deep production experience using XGBoost and IsoForest.
● GCP ML Ecosystem: Advanced operational command over Vertex AI (specifically Pipelines and Custom Training jobs) and native BigQuery Vector Search capabilities.
● Distributed Computing: Extensive experience scaling machine learning and feature preparation pipelines with PySpark (specifically PySpark MLlib/FPGrowth).
● Graph Algorithms: Hands-on proficiency building network topologies, measuring structural properties, and executing community detection algorithms using NetworkX and python-louvain.
● Explainable AI (XAI): Thorough understanding of model evaluation metrics and applying SHAP values to black-box models for enterprise-grade explainability.
Qualifications & Experience
● Experience: Minimum of 3+ years of dedicated experience in Machine Learning Engineering, MLOps, or Data Science Architecture, with a proven track record of taking complex math/statistical algorithms into production.
● Certification: Must hold (or be tracking to achieve immediately) the GCP Professional Machine Learning Engineer certification.
● Engineering Standards: Strong understanding of version control (Git), automated CI/CD deployment logic for ML artifacts, and writing highly modular, performant code.
