> Markdown version of [/jobs/ext/3851954-ai-engineer-platform-and-runtime](https://www.wearedevelopers.com/jobs/ext/3851954-ai-engineer-platform-and-runtime). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Engineer, Platform and Runtime - **Company:** Hedgeserv Corporation - **Location:** Dallas, TX, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Cloud Computing, Continuous Integration, Distributed Systems, Key Management, OAuth, Role-Based Access Control, Reliability Engineering, Openid Connect, Azure Active Directory, Software Engineering, AWS Cdk, Large Language Models, Multi-Agent Systems, Model Validation, Generative AI, HybridCloud, Agentic-AI, Event Driven Architecture, Containerization, AI Platforms, Infrastructure Automation Frameworks, Amazon Bedrock, Model Context Protocol, Terraform, Docker - **Published:** October 21, 2026 - **Apply:** https://www.dice.com/job-detail/70263144-c9b6-4553-bd8a-269adcb3d1e0 ## About the Role * 5+ years of software engineering experience, including at least 1 year delivering LLM or agent-based applications in production. * Demonstrated experience in cloud, platform, site reliability, or software engineering with responsibility for production systems. * Strong enterprise-cloud experience across identity, networking, compute, storage, and event-driven architectures. Hands-on AWS experience is preferred; deep experience with another enterprise cloud and the ability to transfer those skills to AWS are also valued. * Experience with infrastructure as code, containerized workloads, and automated delivery using Terraform, AWS CDK, Docker, ECS, EKS, or comparable cloud-native technologies. * Hands-on experience building or operating production LLM, generative AI, or agent applications using model APIs, structured outputs, tool integration, retrieval, or comparable patterns. * Experience designing or operating distributed systems with asynchronous processing, state management, retries, idempotency, resilience, and recovery. * Working knowledge of observability, incident response, cost management, and enterprise security practices. * Strong analytical, troubleshooting, communication, and collaboration skills, with the ability to work across technical and business teams. Preferred Experience * 7+ years of cloud, platform or software engineering, including substantial production AWS experience and responsibility for architecture. Strong knowledge of identity, networking, compute, storage and event-driven services. * Experience building shared platforms, internal developer products, APIs, SDKs, or reusable services for multiple engineering teams. * Experience leading architecture reviews, establishing technical standards, documenting platforms, or mentoring engineers. * Experience with agentic AI platforms, multi-agent systems, Model Context Protocol, or similar tool and context integration patterns. * Familiarity with OAuth 2.0, OpenID Connect, workload identity, Microsoft Entra ID, or comparable identity platforms. * Experience with AI governance, model evaluation, safety testing, policy enforcement, or lifecycle management. * Experience in financial services or another regulated environment with strong audit, privacy, security, and access-control requirements. * Relevant cloud, security, platform, or AI certifications, or equivalent practical experience. ## Description * Design, build, and operate secure, scalable AI and agent platforms on AWS, applying relevant patterns from other enterprise clouds. * Own platform architecture across infrastructure, AI services, identity, networking, observability, and runtime operations. * Automate infrastructure and delivery using Terraform, AWS CDK, and CI/CD tooling. * Deploy and support production LLM and agent workloads using Amazon Bedrock and related AWS services. * Build resilient distributed systems using asynchronous processing, durable state, retries, idempotency, and recovery. * Own agent-runtime reliability, including scaling, performance, observability, service-level objectives, incident response, pause-and-resume recovery, and cost optimization. * Implement identity and authorization controls, least privilege, encryption, secrets management, and auditable data and tool access. * Govern model access, quotas, provider onboarding, evaluation, and lifecycle controls. * Partner with engineering, architecture, security, product, and business teams to establish reusable standards and patterns.