ML Platform / Integration Engineer

Responsibilities

• Develop and maintain Computer Vision services, APIs, configurations and error-handling mechanisms.
• Package ML services and models for controlled deployment, versioning and rollback.
• Build and maintain automated testing, CI/CD pipelines and release processes.
• Implement health checks, structured logging, monitoring and operational diagnostics.
• Work closely with IT teams on infrastructure, connectivity, certificates, access and environment requirements.
• Support staging and production deployments, including troubleshooting and incident investigation.
• Troubleshoot issues across application, ML model and infrastructure layers.
• Prepare deployment guides, technical documentation, runbooks and operational handover materials.
• Ensure solutions follow relevant security, privacy, access-control and change-management requirements.

Requirements

• 3–8 years of relevant experience in software engineering, platform engineering, system integration or related areas.
• Diploma or Degree in Computer Science, Software Engineering, Information Technology, or a related field
• Strong hands-on Python development experience.
• Practical experience developing and integrating services and APIs.
• Experience with Linux, containers, version control, automated testing and CI/CD.
• Good understanding of monitoring, logging, databases, networking and production support.
• Strong troubleshooting skills across application and infrastructure environments.
• Good technical documentation and communication skills.
• Experience with Kubernetes and Microsoft Azure.
• Exposure to GPU workloads, video streaming or on-premises deployments.
• Experience with ML inference technologies such as ONNX, TensorRT or Triton.
• Previous experience supporting Computer Vision or production AI/ML workloads.