Senior ML Engineer

Sabenza IT & Recruitment; South Africa; On-site; ZAR 1,000,000 - 1,800,000; Full time

Job summary

Sabenza IT & Recruitment is seeking a skilled Platform Engineer to operationalise ML/AI solutions in production. You will deploy models and pipelines on Databricks, build AI agents and GenAI apps, and maintain reusable ML pipelines with CI/CD, testing, monitoring and governance.

You will deploy and manage open source AI models on AKS, design APIs and microservices, and implement containerised solutions with Docker and Kubernetes for scalable, secure deployments.

Qualifications

• Strong understanding of MLOps, DevOps and software engineering practices for ML platforms.
• Experience building, deploying and supporting ML solutions in production.
• Proficiency in Python and API development (SQL/REST).
• Experience with Databricks, MLflow, Model Serving and cloud-native AI platforms.
• Hands-on Kubernetes, Docker and container deployment.
• Experience deploying ML/GenAI on AKS and cloud infra automation.
• Knowledge of CI/CD pipelines, observability and platform monitoring.
• Experience with Spark and large-scale data processing.
• Understanding of LLMs, RAG, and AI agents.
• Ability to translate technical concepts to business outcomes and collaborate with Data Scientists.

Responsibilities

• Productionise, deploy and monitor ML models and data pipelines on Databricks.
• Build, deploy and support AI Agents, GenAI apps and RAG on Databricks.
• Develop reusable ML pipelines with CI/CD, automated tests, monitoring and governance.
• Deploy and manage open source AI models on AKS; design APIs/microservices on AKS.
• Implement containerised solutions with Docker and Kubernetes for scalable deployments.
• Monitor model performance, drift and operational health in production.
• Collaborate with Data Scientists to productionise prototypes into business-ready solutions.
• Mentor junior engineers and promote knowledge sharing.
• Stay current with advancements in AI, GenAI, MLOps, Databricks and cloud tech.

Skills

Databricks Workflows

Model Serving

MLflow

Mosaic AI

AKS

Python

SQL

REST APIs

Docker

Kubernetes

CI/CD

MLOps

Machine Learning

Generative AI

LLM deployment

Cloud engineering

Infrastructure automation

Monitoring

Observability

Troubleshooting

Education

Matric

Tertiary Qualification

Microsoft Azure certs (AZ-104, AZ-305, AI-102)

Databricks certs (Data Engineer, ML Engineer, Generative AI Engineer)

Kubernetes certs (CKA, CKAD)

DevOps / MLOps / Platform Eng certs

AWS/Google Cloud certs beneficial

ML/AI/Data Science certs (MS, Databricks, SAS, Coursera)

Tools

Databricks

MLflow

AKS

Kubernetes

Docker

Python

SQL

REST APIs

Job description

Build, deploy, scale and support machine learning, AI and GenAI solutions in production. The role focuses on operationalising models, developing AI applications and agents, and creating the platforms and services required to deliver business value at scale.

Responsibilities

• Productionise, deploy and monitor machine learning models and data science pipelines on Databricks.
• Build, deploy and support AI Agents, GenAI applications and RAG solutions on Databricks.
• Develop and maintain reusable ML pipelines using MLOps principles, including CI/CD, automated testing, monitoring and governance.
• Deploy, optimise and manage open source AI and machine learning models on Azure Kubernetes Service (AKS).
• Design, develop and support custom APIs and microservices on AKS to expose AI and machine learning capabilities to business applications.
• Implement containerised solutions using Docker and Kubernetes to ensure scalable, secure and resilient deployments.
• Monitor model performance, drift, reliability and operational health in production environments.
• Partner with Data Scientists to productionise prototypes and enable business-ready solutions.
• Collaborate with platform, security, cloud and infrastructure teams to ensure compliance with enterprise standards.
• Troubleshoot and resolve production issues related to models, pipelines, APIs and AI applications.
• Optimise AI and ML solutions for performance, scalability, cost and reliability.
• Contribute to engineering standards, reusable frameworks and best practices across the AI and ML ecosystem.
• Mentor junior engineers and promote knowledge sharing across the team.
• Stay current with advancements in AI, GenAI, MLOps, Databricks, Kubernetes and cloud technologies.

Core Deliverables

• Production-ready ML models and pipelines running on Databricks.
• AI Agents and business applications deployed on Databricks.
• Open source LLMs and AI services deployed on AKS.
• Secure and scalable APIs exposing AI capabilities to consuming systems.
• Automated deployment, monitoring and governance processes.
• Reliable, scalable and compliant AI platforms supporting business outcomes.

Skills

Databricks Workflows, Model Serving, MLflow and Mosaic AIAzure Kubernetes Service (AKS)Python, SQL and REST APIsDocker and KubernetesCI/CD and MLOps practicesMachine Learning and Generative AILLM deployment and optimisationCloud engineering and infrastructure automationMonitoring, observability and troubleshooting

Qualifications

Matric and a Tertiary QualificationMicrosoft Azure certifications (AZ-104, AZ-305, AI-102 or equivalent)Databricks certifications (Data Engineer, Machine Learning Engineer, Generative AI Engineer)Kubernetes and containerisation certifications (CKA, CKAD or equivalent)DevOps, MLOps or Platform Engineering certificationsAWS or Google Cloud certifications will be advantageousMachine Learning, Artificial Intelligence or Data Science certifications from recognised providers such as Microsoft, Databricks, SAS, Coursera or DeepLearning.AI will be an added advantage

Technical / Professional Knowledge

• Strong understanding of MLOps, DevOps and software engineering practices for machine learning platforms.
• Experience building, deploying and supporting machine learning solutions in production environments.
• Proficiency in Python and experience with SQL and API development.
• Experience with Databricks, MLflow, Model Serving and cloud-native AI/ML platforms.
• Hands-on experience with Kubernetes, Docker and containerised application deployment.
• Experience deploying and supporting machine learning and Generative AI solutions on Azure Kubernetes Service (AKS).
• Knowledge of CI/CD pipelines, infrastructure automation and platform monitoring.
• Experience with distributed computing technologies such as Spark and large-scale data processing frameworks.
• Understanding of machine learning, large language models (LLMs), retrieval-augmented generation (RAG) and AI agents.
• Ability to productionise data science solutions and collaborate effectively with Data Scientists.
• Experience delivering end-to-end AI and machine learning use cases from development to production.
• Ability to translate technical concepts into business outcomes and communicate effectively with stakeholders.
• Strong written and verbal communication skills with the ability to work across cross-functional teams.
• Self-driven, adaptable and capable of thriving in a fast-paced, technology-driven environment.