Lead Site Reliability Engineer, ML Platform

About the role

Vinted is looking for a Lead Site Reliability Engineer to own the reliability strategy and architectural evolution of its ML platform. You will ensure that machine learning models, from classic algorithms to Large Language Models, are trained and served with industry-leading stability and performance. You will lead the technical roadmap of the ML Platform, architect high-performance inference solutions and define reliability standards, while mentoring senior engineers.

Key responsibilities

• Lead the technical roadmap of the ML Platform and shape the architectural strategy for serving AI at scale.
• Architect high-performance inference solutions focused on low latency and efficient GPU utilisation across clusters.
• Define reliability standards, including SLOs, error budgets and observability for model-serving systems.
• Mentor and grow senior engineers and foster a culture of technical excellence.
• Solve systemic bottlenecks in the deployment lifecycle by writing RFCs and sparring on long-term architecture.
• Integrate deployment workflows with automated experimentation patterns such as A/B testing and shadow deployments.
• Communicate with stakeholders about architectural risks, planned changes and reliability trade-offs.

Required profile

• Track record of leading technical problem-solving for complex, domain-level systems.
• Deep experience with Kubernetes, Linux internals and high-scale networking.
• Experience with programming or scripting; Go is a plus but other languages are welcome.
• Natural coach and mentor who enables the team rather than writing every line of code.
• Excellent written and spoken English, able to explain technical risks to technical and non-technical audiences.

Required skills

• Kubernetes and Linux internals
• Terraform, Chef, Google Cloud Platform, Go, Kafka, Vespa, Redis, Vitess
• Advantage: GPU workloads and inference frameworks such as KServe, vLLM or NVIDIA Triton

What we offer

• Gross monthly salary of EUR 7,158 to 9,683
• Share option programme and 25 working days of holiday
• Home office support with IT equipment and a furniture budget of up to EUR 540
• Private health insurance and mental health support via the Mindletic app
• Team-building events, a monthly Vinted shopping budget and a workation of up to 90 days per year
• Annual learning budget for courses, certifications and workshops
• Hybrid work with 2 recommended office days, and a dog-friendly office