Spendbase is a global fintech company with a startup mindset, helping businesses optimize their spending on SaaS, cloud services, and corporate cards.
We’re currently growing our LLM API product and are looking for a Middle DevOps Engineer to join the team and help build, maintain, and scale the infrastructure behind it.
LLM API is a standalone, open-source AI infrastructure product that provides a unified API for companies building AI features in production. Instead of integrating directly with multiple LLM providers, teams can use one stable platform to ensure reliability, cost control, and flexibility at scale.
If you enjoy working with high-load systems, cloud infrastructure, Kubernetes, and automation, and want to help build infrastructure for a fast-growing AI product — this role might be for you!
What you’ll do * Build, maintain, and improve the cloud infrastructure behind LLM API * Manage and optimize Kubernetes clusters and containerized applications * Work with AWS services and ensure infrastructure scalability, reliability, and security * Create, maintain, and manage Helm charts * Support and improve CI/CD pipelines and deployment processes * Monitor system performance, troubleshoot incidents, and improve overall infrastructure stability * Work closely with development teams to improve application performance and reliability * Participate in designing infrastructure for high-load and scalable systems * Automate repetitive infrastructure and operational tasks * Work with databases and data infrastructure, including ClickHouse where needed
What we’re looking for * 3+ years of experience as a DevOps Engineer or in a similar role * Strong experience with AWS * Hands-on experience with Kubernetes * Good knowledge and practical experience with Helm and Helm charts * Experience working with high-load and highly scalable systems * Experience with CI/CD tools and infrastructure automation * Strong understanding of Docker and containerization * Experience with monitoring and logging tools * Understanding of networking, security, and cloud infrastructure best practices * Strong problem-solving skills and ability to work independently
Nice to have * Experience with ClickHouse * Experience working with distributed systems * Experience with Infrastructure as Code tools such as Terraform * Experience working with AI, ML, or developer infrastructure products * Experience in a fast-growing startup or product company
What we offer * Competitive salary * Opportunity to grow with a fast-scaling AI product * Ownership-driven, fast-paced environment * Paid vacation, holidays, and sick leave * Online medical consultation services
