MLOps Deployment Specialist

Billennium is a global technology company with over 20 years of experience, focused on innovation and empowering businesses. The role supports a strategic project to consolidate and standardize the MLOps ecosystem, deploying machine learning models from a centralized model registry into multiple production environments.

• Strong hands-on experience with Docker and container orchestration platforms, preferably Kubernetes.
• Proven expertise in building production-grade model serving solutions using REST APIs and/or gRPC.
• Advanced Python programming skills, including automation and deployment workflows.
• Hands-on experience with model registries, preferably Weights & Biases (W&B).

Nice to have:

• Experience with Kubeflow, KServe, Dagster, CI/CD tools (e.g., Jenkins, GitLab CI, ArgoCD), AWS, and Infrastructure as Code practices (e.g., Terraform).

• Design, implement, and document deployment pipelines for models in a consolidated model registry.
• Integrate deployment processes with target environments including Orbital Pipelines, Kubeflow, and KServe.
• Develop wrappers, SDK extensions, and deployment templates for ML frameworks like TensorFlow, PyTorch, and Scikit-learn.
• Collaborate with MLOps teams to establish standards for model serving, monitoring, and endpoint health checks.
• Troubleshoot deployment, packaging, performance, and compatibility issues across ML serving environments.
• Create comprehensive technical documentation and provide knowledge transfer to the internal MLOps team.