Senior AI/DevOps Engineer

Role overview We're looking for a Senior AI/DevOps Engineer who thrives at the intersection of infrastructure, automation, and applied AI. You'll be the person who makes AI-powered features actually ship, scale, and stay healthy in production - building the pipelines, platforms, and guardrails that let the rest of the team move fast with LLMs and ML models. This is a hybrid role: part platform/DevOps engineer, part MLOps practitioner, part AI integrator. This is a full-time, remote role, with flexibility to work from home. This role works across a globally distributed team spanning India and both US coasts, so comfort with asynchronous collaboration and overlapping across time zones is important. Expect some evening hours to overlap with global teams. Responsibility - Design and operate the infrastructure that powers our AI features: LLM integrations, RAG pipelines, vector stores, and model-serving endpoints. - Build and maintain CI/CD pipelines for both traditional services and AI/ML workloads (model deployment, evaluation, rollback). - Own observability and monitoring for AI systems — latency, cost, token usage, output quality drift, and failure modes unique to LLM-based features. Architect and manage cloud infrastructure on Azure (compute, networking, storage, IAM) using infrastructure-as-code. - Containerize and orchestrate services with Docker and Kubernetes. Integrate with AI APIs and platforms (OpenAI, Anthropic, Azure AI/OpenAI Service, or similar) and build internal tooling to make that integration repeatable across teams. Implement guardrails, rate limiting, caching, and cost controls for LLM-powered features. - Collaborate with product, data, and application engineering teams to translate AI-feature designs into reliable, production-grade systems. - Coordinate effectively with teammates across India, East Coast, and West Coast time zones. Apply here https://svitla.com/career/job/senior-aidevops-engineer-1787648291