Senior ML Platform SRE — Hybrid, Reliability & Observability

Vinted; Oslo fylke; Hybrid; NOK 604,000 - 817,000; Full time

Benefits offered by this job

Share options programme

25 working days of holiday

Tools & tech needed for work

Home office budget up to €540

Private health insurance

Mindletic mental health support

Frequent team-building events

Personal monthly shopping budget

Workation up to 90 days/year

Dog-friendly office

Job summary

Vinted is seeking a Senior Site Reliability Engineer to ensure the reliability, scalability, and observability of our ML Platform services, including SLOs and on-call for critical systems like the Vinted Feature Store. You will work with ML platform users and other teams to improve deployment and monitoring capabilities.

You’ll collaborate on Kubernetes, Terraform, and cloud-based tooling, with a focus on building robust automation and runbooks to reduce toil and improve incident response.

Qualifications

• Strong programming background, preferably Go.
• Solid knowledge of Linux operating systems.
• Experience with parts of our technology stack or similar tools.
• Excellent written and spoken English.
• Curious, motivated to grow and deepen expertise in the concepts and technologies used.
• Advantage: GPUs and ML/LLM platforms (Vertex AI, feature stores, model deployment).

Responsibilities

• Deliver deployment solutions with MLOps engineers for production ML models.
• Monitor and improve the Vinted Feature Store to support high RPS and meet SLOs.
• Deploy and maintain self-hosted Langfuse for LLM evaluation and observability.
• Lead reliability work for ML Platform services (SLOs, alerting, toil reduction).
• Build observability and tooling for model deployment and platform services.
• Integrate deployment workflows with automated experimentation (A/B, shadow).
• Communicate incidents, changes, risks, and reliability trade-offs to stakeholders.

Skills

Go language

Linux OS

SRE practices

Observability

English fluency

GPU/ML exposure

Tools

Kubernetes

Terraform

Chef

GCP

Kafka

Vespa

Redis

Vitess

Job description

Vinted is seeking a Senior Site Reliability Engineer to ensure the reliability, scalability, and observability of our ML Platform services, including SLOs and on-call for critical systems like the Vinted Feature Store. You will work with ML platform users and other teams to improve deployment and monitoring capabilities.

You’ll collaborate on Kubernetes, Terraform, and cloud-based tooling, with a focus on building robust automation and runbooks to reduce toil and improve incident response.