AI/ML ENGINEER

• Pharmaceuticals
• Advanced & Smart Manufacturing
• Industry 4.0 Keywords: AI/ML Engineering, Data Engineering, Time-Series ML, Deep Learning, MLOps, Cloud/On-Prem Deployment, Medtech & Pharma Industrial Analytics
  

Role Summary

This Hybrid Role Combines

• Machine Learning (supervised + unsupervised)
• Time-series modelling & Deep Learning
• Data Engineering (ETL/ELT & feature engineering)
• MLOps (CI/CD, containerization, deployment)
• Blueprint/Framework creation for scalable ML implementation
  

Key Responsibilities

• Data Engineering & Feature Development
• Build and maintain ingestion pipelines for time-series and operational datasets.
• Develop structured data layers and reusable feature engineering components.
• Improve data consistency, quality, and ML readiness.
• Implement feature stores for training and real-time scoring.
• Machine Learning Development
  

• Anomaly detection
• Behaviour profiling
• Drift and stability analysis
  

• Prediction/forecasting models
• Regression and classification tasks
  

• LSTM / GRU models
• 1D-CNN
• Temporal Convolutional Networks (TCN)
• Autoencoder architectures
• ML Framework & Blueprint Development
• Develop standardized, reusable ML pipelines that scale across multiple machines, sites, or processes.
• Build modular ingestion, feature engineering, training, scoring, and monitoring components.
• Support replication across MedTech plants, Pharma units, or manufacturing lines.
• MLOps & Deployment
• Containerize ML pipelines using Docker.
• Implement CI/CD workflows (Azure DevOps, GitHub Actions, etc.).
• Deploy models in cloud, on-premise, or hybrid environments.
• Maintain model monitoring, drift alerts, and retraining automation.
• Support API-based and dashboard-based integrations.
• Collaboration & Business Alignment
• Work closely with onsite BAs and domain SMEs to interpret workflows and operational insights.
• Translate business objectives into ML problem definitions and data requirements.
• Communicate ML insights clearly to non-technical manufacturing stakeholders.
• Document assumptions, workflows, and ML model behavior comprehensively.
  

Required Skills & Experience (5–8 Years)

• Strong Python skills (Pandas, NumPy, SciPy, Scikit-learn)
• Experience with Deep Learning (TensorFlow / PyTorch)
• Expertise in time-series modelling and feature engineering
• ETL/ELT pipeline development and data transformation
• Containerization (Docker), Git, CI/CD pipelines
• Cloud familiarity (Azure/AWS) and hybrid deployments
• API development (FastAPI preferred)
  

• Ability to work independently and handle ambiguous or evolving datasets
• Strong analytical and structured problem-solving skills
• Excellent communication skills for cross-functional collaboration
• Comfortable working in regulated environments with strong documentation expectations
  

Preferred Experience

• Experience in MedTech, Pharma, or regulated manufacturing
• Exposure to ISO 13485, GxP, CSV, or validation-aligned documentation
• Familiarity with MES, QMS, Historian, or industrial data sources
• Background in predictive maintenance or operational intelligence solutions
  

Qualifications

• Bachelor’s degree in Computer Science, Data Engineering, AI/ML, or related fields
• Certifications in ML Engineering, MLOps, Cloud, or Industry 4.0 are beneficial