About the role
Nouvells is looking for MLOps Engineers who can build the infrastructure and operational processes required to reliably deploy, monitor, and maintain machine learning systems. You'll bridge machine learning development and production engineering.
As our Founding MLOps Engineer, you will take full ownership of the end-to-end operational lifecycle of Nouvell’s machine learning systems. You will step into a greenfield environment, turning raw exploratory notebooks and prototype models into resilient, containerized, and auto-scaling microservices. You will partner closely with data scientists, backend platform engineers, and operations leadership to define how models are validated, deployed, versioned, served, and monitored across distributed cloud environments.
Key responsibilities
- Design and deploy low-latency, high-concurrency model inference engines utilizing serving frameworks such as Triton Inference Server, vLLM, TensorRT, or TGI.
- Architect and manage scalable GPU/CPU clusters using Kubernetes (EKS/GKE), Ray, or specialized bare-metal GPU cloud providers.
- Build robust feature ingestion, caching, and model registry pipelines using tools like MLflow, Feast, or Weights & Biases.
- Collaborate with Operations to establish incident response runbooks, automated alerts, and cost-allocation dashboards by model workload.
Qualifications
- B.Sc in computer Science or any related field