Overview
Take machine-learning and LLM solutions into reliable, monitored production with sound deployment and evaluation.
What you'll do
- Build CI/CD pipelines and release gates for models, prompts and data
- Run model and prompt registries, versioning and lineage
- Deploy models and LLM services on cloud and Kubernetes
- Monitor drift, quality, latency and cost
- Build feature stores and training pipelines
- Set security, access and audit controls for AI workloads
- Work with data scientists and AI engineers
What you bring
- Hands-on MLOps or ML platform engineering experience
- Python and infrastructure-as-code skills
- MLflow, Kubeflow, SageMaker, Azure ML or similar
- Docker and Kubernetes
- CI/CD tooling and Git workflows
- Observability for production ML or LLM services
- Cloud platform experience on AWS, Azure or GCP
You don't need every item on this list. If most of it fits, send your CV.
Nice to have
- LLMOps tooling such as LangSmith or similar
- GPU workload management
- Data engineering background
- Model validation exposure
- Terraform
- Cloud certifications