Lead ML Platform SRE: Scale GPU-Driven AI (Hybrid)

Vinted; Oslo fylke; Hybrid; NOK 802,000 - 1,084,000; Full time

Benefits offered by this job

The opportunity to benefit from our

share options programe

25 working days of holiday

Access to all the tools & tech needed

Home office support: up to €540 for家具

Job summary

Vinted is seeking a Lead Site Reliability Engineer to own the reliability strategy and architecture for our ML platform. You will mentor senior engineers and shape platform standards while guiding GPU-heavy workloads across production, training, and LLM serving.

You’ll collaborate with Data Scientists and Platform teams to translate ML innovation into production, manage a large GPU fleet, and drive scalable, reliable AI delivery at scale.

Qualifications

• Track record of leading technical problem-solving for complex systems.
• Deep experience with Kubernetes, Linux internals, and high-scale networking.
• Experience with programming or scripting (Go a plus).
• Choose the right tool for the job based on long-term impact.
• Excellent written and spoken English, able to communicate risks to diverse stakeholders.
• Natural coach and mentor who enables team success.
• Advantage: GPU workloads and inference frameworks (KServe, vLLM, NVIDIA Triton).

Responsibilities

• Lead the technical roadmap for the ML Platform, ensuring training and inference infrastructure scales.
• Architect high-performance inference solutions, focusing on low-latency delivery and efficient GPU utilisation.
• Define and drive reliability standards, including SLOs, error budgets, and observability.
• Mentor and grow senior engineers within the team, fostering technical excellence and learning.
• Identify and solve systemic bottlenecks in deployment lifecycle; write RFCs.
• Oversee deployment workflows with A/B testing and shadow deployments.
• Communicate architectural risks and strategic reliability trade-offs.

Skills

Go

High-scale networking

Mentoring

Leadership

English communication

Tools

Kubernetes

Linux

Job description

Vinted is seeking a Lead Site Reliability Engineer to own the reliability strategy and architecture for our ML platform. You will mentor senior engineers and shape platform standards while guiding GPU-heavy workloads across production, training, and LLM serving.

You’ll collaborate with Data Scientists and Platform teams to translate ML innovation into production, manage a large GPU fleet, and drive scalable, reliable AI delivery at scale.