AI/ML Platform Engineer (Kubernetes & MLOps)
At a Glance
- Category
- 💻 Technology
- Level
- Mid-Level
- Type
- Full-time
Spot the Problem
- Find what's costing you interviews at Jobs for Humanity
- Get AI-rewritten bullet points
- Download Gulf-ready CV
60 seconds. $5.88 one-time.
Company Description
Jobs for Humanity is partnering with Kanz 30 to build an inclusive and just employment ecosystem. Therefore, we prioritize individuals coming from all walks of life.
Company Name: Kanz 30
Job Description
We are seeking an MLOps/AI Platform Engineer to build, deploy, and scale production AI/ML services on Kubernetes. You will partner with ML engineers and software teams to operationalize models with strong reliability, performance, and cost efficiency using automated pipelines, monitoring, and end-to-end MLOps practices.
Job Purpose
Own the deployment and operational excellence of AI/ML services by establishing robust CI/CD, model serving, observability, and lifecycle management on Kubernetes—optimizing inference performance (latency/throughput), ensuring reliable releases, and reducing infrastructure and operating costs.
Job Duties and Responsibilities
- Kubernetes
- Docker
- CI/CD (GitHub Actions/Jenkins)
- Python
- REST/gRPC model serving
- MLflow
- TensorFlow or PyTorch
- Prometheus/Grafana
- Kafka/RabbitMQ
- Monitoring and alerting
- Automated MLOps practices
- Model performance optimization
- Cost optimization
Qualifications
Required Qualifications
- Kubernetes
- Docker
- Python
- MLflow
- TensorFlow or PyTorch
- REST/gRPC model serving
- CI/CD (GitHub Actions/Jenkins)
- Prometheus/Grafana
- Kafka/RabbitMQ
- AWS/GCP/Azure basics
- Monitoring and incident response
- MLOps/production AI experience
Requirements
- •Kubernetes proficiency
- •Docker experience
- •Python programming skills
- •MLflow experience
- •TensorFlow or PyTorch knowledge
- •REST/gRPC model serving
- •CI/CD (GitHub Actions/Jenkins)
- •Prometheus/Grafana monitoring
Responsibilities
- •Own deployment and operational excellence of AI/ML services
- •Establish robust CI/CD, model serving, observability, and lifecycle management on Kubernetes
- •Optimize inference performance (latency/throughput)
- •Ensure reliable releases
- •Reduce infrastructure and operating costs
- •Partner with ML engineers and software teams to operationalize models
Related Jobs4 similar jobs
Browse Similar
- Find what's costing you interviews at Jobs for Humanity
- Get AI-rewritten bullet points
- Download Gulf-ready CV
60 seconds. $5.88 one-time.
Jobs for Humanity is a global organization focused on connecting companies with diverse talent, including individuals with disabilities. They aim to foster inclusive employment practices worldwide.