ML Architect

This is a senior, hands-on architecture role focused on building production-grade ML systems for our regtech and fintech platforms.

The candidate should be able to design scalable ML systems, guide ML engineers, work closely with data engineering and backend teams, and ensure that models are explainable, auditable, secure, and suitable for regulated business environments.

Key Responsibilities

• ML Architecture & Strategy
  
  • Design the end-to-end ML architecture for risk scoring, fraud detection, anomaly detection, behavioural analysis, entity resolution, alert prioritization, and predictive intelligence.
  • Define the ML roadmap in collaboration with Product, Compliance, Data, Engineering, and DevOps teams.
  • Select the right ML approach for each use case, including supervised learning, unsupervised learning, graph analytics, rules-assisted ML, anomaly detection, NLP, or hybrid models.
  • Design ML systems for multi-tenant SaaS deployment across cloud environments.
  • Ensure ML solutions are scalable, reusable, secure, and production-ready.
• Model Design & Governance
  
  • Define standards for feature engineering, model training, validation, versioning, deployment, monitoring, and retraining.
  • Ensure models are explainable, auditable, and suitable for business and compliance users.
  • Create model governance practices including model documentation, model approval, performance benchmarking, drift monitoring, and periodic review.
  • Design champion/challenger model frameworks to continuously improve model performance.
• ML Platform & MLOps Design
  
  • Define the architecture for feature stores, model registries, experiment tracking, training pipelines, inference APIs, batch scoring, and model monitoring.
  • Work with DevOps, SRE, cloud, backend, and security teams to deploy models safely into production.
  • Design real-time and batch inference workflows.
  • Ensure ML systems are cost-efficient, reliable, and secure.
• Technical Leadership
  
  • Guide ML Engineers, Data Engineers, GenAI Engineers, and MLOps resources on technical approach.
  • Review model design, data quality, evaluation metrics, code quality, and deployment readiness.
  • Translate business problems into clear ML use cases and technical designs.
  • Create internal ML standards, documentation templates, and review practices.

Required Experience

• 10+ years of experience across software engineering, data science, machine learning, or AI engineering.
• 5+ years of hands-on experience building and deploying ML models in production.
• Strong experience with classification, clustering, anomaly detection, risk scoring, entity matching, graph analytics, and predictive modelling.
• Experience designing ML systems for SaaS, fintech, banking, payments, fraud, compliance, or risk platforms is strongly preferred.
• Experience with cloud ML architecture on AWS and/or GCP.
• Prior experience leading ML engineers or working as a technical ML lead/architect.

Required Technical Skills

• Python, SQL, Pandas, NumPy, Scikit-learn.
• XGBoost, LightGBM, CatBoost, TensorFlow, or PyTorch.
• Feature engineering, model evaluation, model explainability, and drift detection.
• MLflow, SageMaker, Vertex AI, Kubeflow, Airflow, or similar tools.
• Batch and real-time inference architecture.
• APIs, microservices, data pipelines, and cloud deployment.
• Data quality, data lineage, and model governance.

Good to Have

• Graph ML or graph database experience.
• Entity resolution and name-matching experience.
• Fraud, risk, payments, customer intelligence, or compliance analytics experience.
• NLP or text classification experience.
• LLM integration, RAG, or GenAI-assisted workflow experience.
• Experience working in regulated environments with audit and governance requirements.

Must Requirement
Candidate must have already designed and deployed ML models into real production systems, not just notebooks or research projects. Demonstrated experience to challenge weak ML design, guide engineers, work with business teams, and build models that are explainable, measurable, and production-ready.

ATS Keywords
Machine Learning Architect, ML Architect, AI Architect, Machine Learning, MLOps, Model Deployment, Model Governance, Feature Engineering, Risk Scoring, Fraud Detection, Anomaly Detection, Entity Resolution, Graph Analytics, Behavioural Analytics, Predictive Modelling, XGBoost, LightGBM, Scikit-learn, Python, SQL, AWS SageMaker, GCP Vertex AI, MLflow, Model Monitoring, Model Drift, Explainable AI, SaaS, FinTech, RegTech, Compliance Analytics.