Senior MLOps Engineer, Buyer

VintedAmsterdamHybridFull-time1 week ago

Vinted is hiring a Senior MLOps Engineer for its Buyer domain to productionise critical ML systems like ranking, retrieval, and recommendations. The role focuses on migrating experimental model training code to robust automated pipelines, building continuous training workflows, and automating model serving on GCP/Vertex AI, Vespa, and Triton. Requires deep expertise in GCP/Vertex AI, Kubernetes, Docker, and CI/CD automation, with a strong service mindset to bridge Data Science and Infrastructure.

What you'll do

Productionise ML models: migrate existing model training code from experimental or proof-of-concept stages to robust and automated pipelines
Build continuous training (CT) pipelines: design, build, and maintain automated workflows for data preparation, model training, and batch scoring
Automate model serving & integration: package and deploy traditional ML models (e.g., in ONNX format) to existing serving infrastructure, primarily Vespa and/or Triton
Close the deployment loop: automate model deployments where they are still manual, e.g., building a GitHub Action that deploys a new model to Vespa, triggered by a webhook from a successful Vertex AI training pipeline
Build the missing quality gates: build automated quality and evaluation gates that pipelines lack today
Establish and uphold ML Model Lifecycle Standards: take ownership of and continuously improve the standards, quality, and governance of the complete ML model lifecycle

What you need

Must-have

GCPVertex AIKubernetesDockerCI/CDGitHub ActionsJenkinsMachine Learning

Nice-to-have

VespaNVIDIA TritonONNXSageMaker

Soft skills

service mindsetcommunicationbridge between teamspragmatismbig-picture thinkingcuriosityproblem-solving

MLOpsMachine LearningGCPVertex AIKubernetesDockerCI/CDVespaTritonSenior

/What you'll do

/What you need

Must-have

Nice-to-have

Soft skills

What you'll do

What you need