MLOps Engineer

MLOps Engineer

Recruiter:

A 1L Realization (Pty) Ltd

Job Ref:

JHB000996/Tshid

Date posted:

Thursday, July 2, 2026

Location:

Johannesburg, South Africa

SUMMARY:

Our client in the Network Communications sector is looking for an MLOps Engineer on a contract duration of 6 months.

Role Purpose

The MLOps Engineer is responsible for operationalising machine learning models into scalable, reliable and production-ready services. The role focuses on deploying, monitoring, maintaining and continuously improving ML models in production environments. Model development and feature engineering are owned by the FTE ML Engineer; this role ensures that models are effectively served, monitored and retrained within robust MLOps pipelines aligned to enterprise standards.

POSITION INFO:

Key Responsibilities Deploy machine learning models into production environments using scalable and automated deployment practices. Build and maintain model serving infrastructure for real-time and batch inference use cases. Implement monitoring frameworks to track model performance, drift, latency, data quality and service reliability. Automate model retraining pipelines in collaboration with ML Engineers and Data Engineers. Manage model versioning, deployment lifecycle and rollback strategies. Operationalise CI\/CD pipelines for machine learning workflows in collaboration with Platform Engineering teams. Ensure model deployments comply with security, governance, privacy and enterprise architecture standards. Support incident management, root cause analysis and resolution of model performance issues in production. Optimise model inference performance, scalability and cost efficiency across cloud environments. Collaborate with ML Engineers, Data Scientists, Big Data Engineers and Platform Engineers to ensure smooth transition from development to production. Maintain documentation for model deployment processes, monitoring dashboards and operational procedures. Qualifications \& Experience Bachelor's degree in Computer Science, Data Science, Information Technology, Engineering or a related field. 5-8 years' experience in Machine Learning Engineering, DevOps or MLOps roles. Strong experience deploying and maintaining machine learning models in production environments. Hands-on experience with model serving frameworks and MLOps tools (e.g. MLflow, Kubeflow, Sagemaker, Azure ML or similar). Experience with containerisation and orchestration technologies such as Docker and Kubernetes. Strong programming skills in Python and experience with REST APIs and microservices. Experience with cloud platforms such as Azure, AWS or Google Cloud Platform. Knowledge of model monitoring, drift detection and performance evaluation techniques. Experience with CI\/CD pipelines for machine learning workloads is highly desirable. Key Competencies MLOps and model lifecycle management Model deployment and serving Monitoring and observability CI\/CD for ML systems Cloud computing and containerisation Python development API and microservices integration Model governance and version control Troubleshooting and incident resolution Collaboration in Agile delivery environments