Brief about the role : Candidate is expected to productionalize & deploy the model code (base code will be developed by Data Science). This role will have to spend good amount of time in Scaling the pre-developed model training and inference (multi-GPU/CPU).  We expect the candidate to have Strong Python/SQL , Kubernetes, Scaled Model deployment and ML experience.

About the Role:

We are seeking a highly skilled MLOps Engineer to play a pivotal role in bringing cutting-edge AI models to production. You will collaborate closely with our Data Science and Machine learning teams to optimize, scale, and deploy AI/ML models.

Responsibilities:

• Model Productionization and Deployment:
  • Translate complex machine learning models into robust and scalable production systems.
  • Deploy models to production environments using Kubernetes or other container orchestration tools.
  • Ensure seamless integration of models with existing infrastructure and applications.
• Performance Optimization:
  • Identify and implement strategies to optimize model training and inference performance.
  • Leverage techniques like GPU acceleration, distributed training, and model quantization to improve efficiency.
  • Monitor model performance in production and proactively address any performance bottlenecks.
• Scalability Engineering:
  • Design and implement scalable solutions for handling large-scale data and model workloads.
  • Optimize data pipelines and model serving infrastructure to meet growing demands.
  • Collaborate with infrastructure teams to ensure adequate resources and capacity.
• ML Operations (MLOps):
  • Establish and maintain robust MLOps practices to streamline model development, deployment, and monitoring.
  • Implement automated pipelines for model training, testing, and deployment.
  • Monitor model performance in production and take corrective actions as needed.

Qualifications:

5+ years of experience

• Strong proficiency in Python programming language and SQL.
• In-depth knowledge of machine learning frameworks (e.g., TensorFlow, PyTorch, Scikit-learn).
• Expertise in Kubernetes or other container orchestration tools. – Good to have
• Deploying Code & Optimizing
• Experience with MLOps tools and frameworks (e.g., MLflow, Kubeflow).
• Version Controlling – Azure blob storage
• Experience with cloud platforms (e.g., AWS, GCP, Azure). – Azure is preferred
• Solid understanding of distributed computing and parallel programming.
• Strong problem-solving and analytical skills.
• Excellent communication and collaboration abilities.

Preferred Qualifications: ¹   Good to have

• Knowledge of big data technologies (e.g., Hadoop, Spark).
• Experience with model optimization techniques (e.g., pruning, quantization, distillation).