• Design and implement Retrieval-Augmented Generation (RAG) architectures. • Build AI-powered chatbot experiences using AWS Bedrock. • Develop multi-source data ingestion and retrieval pipelines. • Design and optimize embeddings and semantic search strategies. • Build scalable vector search solutions for enterprise knowledge retrieval. • Integrate structured and unstructured data sources into AI workflows. • Develop prompt engineering strategies to improve response quality and accuracy. • Build cloud-native AI services using AWS. • Collaborate with engineering teams to improve AI performance, scalability, and reliability. • Continuously evaluate new AI technologies and best practices for enterprise LLM applications.

• Design and develop enterprise AI solutions using AWS Bedrock. • Build AI-powered workflow automation for complex business processes. • Develop AI agents using AWS Bedrock Agents and Guardrails. • Integrate enterprise platforms, including ServiceNow and SAP. • Develop secure REST API integrations across enterprise applications. • Build Retrieval-Augmented Generation (RAG) pipelines using enterprise knowledge bases. • Develop document-processing workflows, including PDF extraction and business-rule validation. • Design cloud-native backend services using AWS. • Build scalable React interfaces for AI-powered business applications. • Develop GenAI CI/CD pipelines and automation workflows. • Implement Responsible AI principles and governance across AI solutions. • Collaborate with engineering and business teams to continuously improve AI capabilities.

• Lead the EverHealth Cloud Engineering team responsible for AWS infrastructure, cloud platform standards, cloud cost management, and infrastructure-as-code maturity • Prioritize Cloud Engineering work during sprint planning in partnership with the Scrum Master • Manage, coach, develop, and performance-manage Cloud Engineering team members • Ensure technical alignment with the Principal Cloud Platform Engineer • Own AWS account structure, landing zones, networking, IAM standards, and environment provisioning practices • Own Terraform strategy, reusable infrastructure patterns, IaC standards, and review practices • Build and mature cloud architecture standards across the EverHealth product portfolio • Support AWS services and environments including VPC, IAM, EC2, ECS/EKS, RDS, S3, CloudWatch, load balancers, networking, backup/DR, Windows/Linux workloads, and related services • Lead and contribute hands-on to cloud infrastructure design and implementation using Terraform, Ansible, Spacelift, GitHub, and related tooling • Drive cloud cost optimization analysis and recommendations in partnership with Product Engineering • Identify opportunities to improve utilization, reduce waste, and align cloud/infrastructure spend with business needs • Reduce cloud operational risk through better standards, automation, documentation, reusable patterns, and repeatable practices • Implement cloud security standards defined by Security, while helping guide cloud security architecture where infrastructure design decisions create risk or require platform-level judgment • Lead cloud modernization efforts across EverHealth products, including legacy infrastructure reduction, data center migration, AWS environment modernization, and product-specific cloud improvements • Help mature container and Kubernetes platform practices in partnership with Product Engineering • Ensure Cloud Engineering serves as a senior escalation point for cloud infrastructure issues when SRE cannot resolve the issue and the root cause is within AWS or related infrastructure services • Use CloudWatch, Grafana, New Relic, Sentry, OpsGenie/Jira Service Management Operations, and related observability or operational tools to support cloud infrastructure troubleshooting and production visibility • Partner with Product Engineering on architecture reviews, environment buildouts, implementation support, modernization planning, and cloud infrastructure escalations • Partner with SRE on AWS infrastructure reliability, production readiness, operational resilience, disaster recovery, and business continuity practices • Partner with Delivery Engineering and Enablement Engineering on cloud deployment processes, CI/CD infrastructure, shared services, release support, and environment standards • Partner with the Program Manager, Technical Project Manager, and Scrum Master to collect and share cloud health, cloud cost, operational risk, modernization progress, and project health for Cloud Engineering-supported work • Partner with Security and Compliance on IAM, encryption, network controls, logging, auditability, HIPAA infrastructure controls, and secure cloud operations • Establish and mature Cloud Engineering operating cadence, including architecture reviews, backlog reviews, cost reviews, security reviews, operational risk reviews, and standards reviews • Challenge product teams and partner functions when cloud architecture, cost, security, or operational decisions create unacceptable risk • Help create a high-performing Cloud Engineering culture rooted in ownership, platform leverage, practical standards, automation, and continuous improvement

Role Description Everforth ECS is seeking an OpenShift Cloud Engineer to work in a remote capacity. Ability to meet on-site at ECS’ Fairfax, VA office once a week is preferred, but not required. This exciting opportunity will support the modernization of a DHS system to the Oracle Cloud Infrastructure (OCI) cloud. This role will function as an OpenShift subject matter expert (SME) and coordinate with cloud and on-premise infrastructure teams to develop, deploy, optimize, and support multiple Red Hat OpenShift deployments in OCI. - OpenShift Architecture and Administration: - Develop, plan, and execute deployment of OpenShift environments at any impact level (IL2-IL6) and within cloud, on-premise, or hybrid infrastructures. - Documentation and adherence to security policies as mandated by ATO requirements. - Advise Project Management, Customer leadership, and partner teams on migration to OpenShift operations. - OpenShift Operational Support: - Support onboarding of customer and partner teams into supported OpenShift deployments. - Coordinate with Project Management teams and partners to ensure appropriate resourcing while operating within provided budgetary guidance. - Function as SME for existing Cloud and Infrastructure teams and facilitate cross-training and documentation to expand OpenShift knowledge within the existing team. - OpenShift Troubleshooting and Support: - Troubleshoot production failures. - Support partners and customers with troubleshooting operational failures. - Maintain security compliance and develop/execute remediations, patching, and POAMS as necessary to maintain security compliance and ATO status. - Successfully communicate to customers, contract program managers, industry partners, ECS senior management, and Government representatives. - Track industry trends and leverage them to drive innovation and solution excellence across various functional domains. Qualifications - Bachelor's degree or equivalent experience. - Ability to pass a DHS Public Trust investigation. - 12+ years of relevant experience in the progression of roles to include delivering and sustaining technical and cloud solutions. - DOD 8570-01M certification: IAM Level I or better (e.g., Security+). - Expertise with OpenShift Architecture and Administration: To include cluster configuration, updates, backup/restore, networking, storage, security, and performance. - Expertise with RHEL and OpenShift. - A strong understanding of cloud-based technologies with a desire to learn more. - Demonstrated customer focus and strong analytical and problem-solving skills. - Strong verbal and written communications skills. Requirements - Salary Range: $175,000-$210,000 Benefits - General Description of Benefits