DevOps / Infrastructure & AI LLM Systems Engineer (Hybrid) Yuma AI

Senior DevOps / Infrastructure & AI LLM Systems Engineer (Hybrid) Yuma AI (YC W23) - Join as our first dedicated DevOps/Infrastructure Engineer. This foundational role gives you full ownership of cloud infrastructure, deployments, reliability, and scaling. Over the past two years, we built a large amount of core tech, and the surface ahead is even larger as we scale usage, models, and automation. You will keep our platform fast, reliable, and ahead of the curve. What You Will Own: - Infrastructure & Platform: - All cloud infrastructure across AWS, GCP, and Azure. - Kubernetes cluster management, scaling, upgrades, and security. - CI/CD pipelines (GitHub Actions) and deployment systems. - Observability, monitoring, logging, alerting, and reliability practices. - Incident response, on-call rotation, and uptime improvements. - Cost optimization and infra-level performance tuning. - Security best practices, IAM, secrets, policies, and overall infra hygiene. - Backend & Data Systems: - High-scale PostgreSQL (large DB, indexes, performance tuning). - Redis and Sidekiq pipelines, queue scaling, job parallelization. - API performance and throughput. - AI / LLM Systems: - Manage and optimize LLM deployments across cloud providers. - Improve latency, reliability, and cost through routing and system architecture. - Help build and maintain eval pipelines and A/B tests. - Contribute directly at the app level (prompts, agents, routing). - Support or prototype self-hosted model experiments (optional but valuable). The Ideal You: - 8+ years of experience in DevOps / infrastructure roles, ideally in fast-paced SaaS or startup environments. - Scaled production systems before and knows how systems behave under real load. - Comfortable deep in Kubernetes or writing Ruby/Python for quick scripts, tools or LLM eval. - Enjoys working on AI systems and has hands-on experience with LLM-powered applications. - Toolkit includes: Kubernetes, Docker; AWS, Azure, GCP

(strong in at least 2); GitHub Actions CI/CD; PostgreSQL, Redis, Sidekiq; LLM APIs (OpenAI, Azure, Anthropic; self-hosted a plus); Terraform or similar IaC; strong coding ability to contribute across the stack. The Alternative You: If you're early in your career but have strong infrastructure experience and clear upside, and you can reasonably grow into the full scope within 2-3 years, feel free to reach out. Raw talent is welcome. Why Yuma? - High impact with ownership from day one. - Competitive compensation based on experience and stock options. - Fast growth - fast learning curve; exposure to AI, product iteration, customer workflows, and cross-functional problem solving. - Work closely with founders and product/engineering leadership; your ideas directly influence the roadmap. - A culture of ownership, transparency, and continuous improvement; we move fast, iterate constantly, and empower people to grow. - Flexibility: fully remote in Europe with preference for