Technical lead for MLOps infrastructure, owning design and implementation of production-grade ML pipelines, infrastructure-as-code automation, and model lifecycle management. Overall Tech Lead for the project: drives architectural decisions, sets technical standards, and ensures the ML platform is reliable, scalable, and compliant with operational and regulatory requirements (validation and reproducibility standards for HCLS AI).
Activities:
- Architect and implement end-to-end MLOps pipelines: CI/CD for model training, evaluation, approval, deployment with audit trails
- Design and deploy infrastructure-as-code using Terraform for all ML platform resources
- Build automated training jobs on Amazon SageMaker: hyperparameter tuning, distributed training, spot optimization for life sciences workloads
- Implement model performance monitoring: data drift detection, prediction quality tracking, automated retraining triggers
- Establish CI/CD for ML artifacts: model versioning, container builds, integration testing, staged rollouts with validation gates
- Design model registry and artifact management for governance, reproducibility, and 21 CFR Part 11 compliance
- Implement infrastructure monitoring, alerting, and auto-scaling for training and inference workloads
- Define and enforce MLOps best practices, coding standards, and architectural patterns
- Serve as overall Tech Lead: architecture reviews, mentoring, technical decision-making
- Coordinate with customer platform, IT security, and quality teams on networking, security, and compliance
