Job Title

EPMA is looking for an AI DevOps & Infrastructure Engineer for in-house project.Title: AI DevOps & Infrastructure EngineerLocation: 100% RemoteResponsibilities:Build and maintain hybrid AI environments (AWS + on-prem DGX)Automate infrastructure provisioning with Terraform, Helm, or CloudFormationManage Kubernetes clusters, namespaces, and workload isolationImplement CI/CD pipelines (GitHub Actions, GitLab CI/CD, Argo, etc.)Monitor system performance with Prometheus, Grafana, ELKSecure systems with RBAC, IAM, TLS, and VaultSupport deployment of LLMs, RAG agents, and model pipelinesMust-Have Skills:3+ years in DevOps, preferably supporting ML or AI workloadsStrong experience with Docker, Kubernetes, TerraformHands-on with AWS (EC2, S3, IAM, KMS, VPCs)Experience supporting ML pipelines with Airflow, MLFlow, or KubeflowProficiency in Linux server administrationUnderstanding of networking, DNS, and VPNsAbility to work with AI/ML engineers collaborativelyNice-to-Haves:Familiarity with LLM deployment tools (vLLM, DeepSpeed, TGI, etc.)Experience with vector databases (Pinecone, Weaviate, FAISS)Security certifications or experience with GDPR, HIPAA, SOC2 compliancePast experience supporting ethical AI projects or autonomous systemsWhy Join EPMA?As a people-first company with a sharp focus on innovation and AI, EPMA empowers team members to grow professionally while making a real impact. Join a team where your organizational superpowers are valued—and where your role plays a key part in driving operational excellence.