Senior Site Reliability Engineer, ML Platform

As Senior Site Reliability Engineer, you will be responsible for the reliability, scalability, observability, and operational excellence of Vinted’s ML Platform services including SLOs/alerting, incident response, capacity planning, automation, and on-call for critical services such as the Vinted Feature Store. You’ll join the ML Platform team, which owns the tooling for ML/LLM development, deployment and other platform capabilities that increase ML/AI delivery speed at Vinted. You will be working closely with ML platform users, Data Infrastructure and Production Engineering teams.

Here are some of the technologies we use: Kubernetes, Terraform, Chef, Google Cloud Platform, Go, Kafka, Vespa, Redis, Vitess.

• Work with MLOps engineers to deliver deployment solutions that enable Data Scientists to seamlessly deploy any ML model to production.
• Monitor and improve the Vinted Feature Store to reliably support 240k feature-read RPS while meeting SLOs.
• Participate in deploying and maintaining self-hosted Langfuse for LLM evaluation and observability (upgrades, automation, security hardening).
• Lead reliability work for ML Platform services (SLOs, alerting, runbooks, postmortems, toil reduction).
• Build up observability and operational tooling for model deployment and platform services.
• Assist with integrating deployment workflows with automated experimentation (A/B, shadow).
• Communicate with stakeholders about incidents, planned changes, risks, and reliability trade-offs.

• Have working experience with programming or scripting (Go is a plus, but experience with other languages is also welcome).
• Have a solid understanding of Linux operating systems.
• Have experience in parts of our technology stack or have worked with similar tools and platforms.
• Excellent written and spoken English.

Nice to have

• Advantage: experience with GPUs and ML/LLM platforms (Vertex AI, feature stores, model deployment).

• The opportunity to benefit from our share options programme
• 25 working days of holiday
• Access to all the tools & tech needed for work
• Home office support: we provide IT workstation equipment and a personal budget of up to 540 for home workplace furniture
• Private health insurance
• Mental and emotional health support through the Mindletic app
• Frequent team-building events
• A personal monthly budget for shopping on Vinted
• The opportunity to spend up to 90 days per year - 21 of which can be spent working outside of the EU - on workation
• A dog-friendly office
• In Vilnius office: Gym & in-house meals at friendly prices
• In Kaunas office: a monthly lunch allowance, and a once-a-week provided in-house lunch and breakfast