onsite
AI Support Engineer - YER
Software Engineer
Support and maintain AI-driven services, ensuring high availability and performance using Python, ML frameworks, and cloud infrastructure on AWS. Collaborate with data scientists and DevOps to deploy, monitor, and troubleshoot AI models in production.
About the role
Key Responsibilities
- Deploy and maintain AI models and inference pipelines on AWS, ensuring scalability and reliability.
- Collaborate with data science teams to translate model artifacts into production-ready services.
- Implement monitoring, logging, and alerting for AI workloads using Prometheus, Grafana, and CloudWatch.
- Automate deployment workflows with Docker, Kubernetes, and CI/CD pipelines (GitHub Actions, Jenkins).
- Diagnose and resolve performance bottlenecks, memory leaks, and deployment failures.
- Document best practices, runbooks, and troubleshooting guides for internal teams.
Requirements
- 3+ years of experience in AI/ML operations or related roles.
- Strong proficiency in Python and experience with ML frameworks (TensorFlow, PyTorch).
- Hands‑on experience with AWS services (ECS/EKS, S3, Lambda, SageMaker).
- Solid knowledge of containerization (Docker) and orchestration (Kubernetes).
- Experience with CI/CD tooling and infrastructure as code (Terraform, CloudFormation).
Skills
pythonmachine learningawsdockerkubernetescicd