<p>Kforce has a client in Greenwood Village, CO that is seeking a DevOps Engineer/Machine Learning Operations.</p> <p>Summary: Our client is seeking a skilled Kubernetes & ML Ops Engineer to join their fast-paced, collaborative DevOps and Data Science team. This role focuses on deploying and operating scalable AI/ML services on AWS EKS, managing vector databases, and integrating cutting-edge AI services like Azure OpenAI APIs. If you have a passion for Kubernetes mastery, AI/ML workload operationalization, and secure enterprise AI deployment, this opportunity is for you.</p> <p>Responsibilities:</p> <ul> <li>Deploy and manage microservices, including APIs, Docker-based services, and vector stores on Amazon EKS </li><li>Ensure 24/7 cluster uptime and seamless service connectivity </li><li>Validate stability and performance of deployed configurations and services </li><li>Manage PostgreSQL with pgvector for embedding storage </li><li>Securely expose and integrate vector databases within Kubernetes environments </li><li>Monitor and troubleshoot database performance issues </li><li>Implement and maintain CI/CD pipelines using GitLab </li><li>Use Terraform for Infrastructure as Code (CloudFormation experience a plus) </li><li>Automate build, test, and deployment workflows </li><li>Set up monitoring dashboards and alerting via Datadog (Splunk or alternatives welcomed) </li><li>Ensure full visibility into system health, latency, and uptime metrics </li><li>Collaborate with data science teams to operationalize ML workloads </li><li>Support Retrieval-Augmented Generation (RAG) architectures and vector-based search </li><li>Integrate securely with Azure OpenAI APIs, including implementing internal guardrails* Proven expertise managing scalable production Kubernetes workloads on EKS (or equivalent) </li><li>Hands-on experience with PostgreSQL + pgvector; Knowledge of other vector stores like Pinecone, Weaviate, or Milvus is a plus </li><li>Solid conceptual understanding of LLMs, embeddings, retrievers, and RAG systems </li><li>Familiarity with OpenAI services and API-based LLM workflows </li><li>Highly collaborative DevOps/Data Science team with a strong emphasis on secure and ethical AI usage </li><li>Fast-paced environment dedicated to pushing the boundaries of enterprise AI capabilities </li></ul> <p>Nice to have:</p> <ul> <li>Experience deploying AI/ML workloads on AWS, Azure, or GCP </li><li>Exposure to cloud-native AI services such as SageMaker, Azure ML, or Vertex AI </li><li>Understanding of compliance and security guardrails related to LLM deployments </li><li>Knowledge of service meshes or API gateways for secure model exposure </li></ul>