Senior SRE Engineer – Cloud AI Reliability & Scale

Google; Warszawa; On-site; PLN 364,000 - 373,000; Full time

Job summary

Google in Warsaw, Poland is hiring a Senior Software Engineer in Site Reliability Engineering for the Vertex AI 3P platform. The role focuses on building rock-solid, scalable infrastructure for third-party model deployments on a GKE-based serving stack, balancing reliability and performance for Google Cloud services.

You will work with teams to drive incident response, capacity planning, and system optimization, mentoring junior engineers and shaping the overall reliability strategy across

Qualifications

• Bachelor's degree or equivalent practical experience in CS or related field.
• At least 5 years of software development experience.
• At least 3 years leading projects and providing technical leadership.
• At least 3 years designing, analyzing, and troubleshooting large-scale distributed systems.

Responsibilities

• Engage in and improve the lifecycle of services from inception to deployment, operation and refinement.
• Support services before go-live through system design consulting, platform development, capacity planning and launch reviews.
• Maintain services post-launch by monitoring availability, latency and health.
• Scale systems sustainably via automation and reliability improvements.
• Practice blameless post-mortems and incident response.

Skills

Software development

Technical leadership

Mentoring

Distributed systems

Education

Bachelor's degree in Computer Science

Tools

GKE

Google Cloud

Cluster management

Load balancing

pprof (Performance profiling)

Job description

Google in Warsaw, Poland is hiring a Senior Software Engineer in Site Reliability Engineering for the Vertex AI 3P platform. The role focuses on building rock-solid, scalable infrastructure for third-party model deployments on a GKE-based serving stack, balancing reliability and performance for Google Cloud services.

You will work with teams to drive incident response, capacity planning, and system optimization, mentoring junior engineers and shaping the overall reliability strategy across