Senior AI Platform & Runtime Engineer (AWS)

HedgeServ Corporation; Texas; Hybrid; USD 150,000 - 210,000; Full time

Job summary

HedgeServ Corporation in the United States is seeking a Senior AI Platform and Runtime Engineer to design, build, and run HedgeServ’s shared AWS platform for AI agents and applications. You will own runtime infrastructure, identity, security, model access, deployment, and reliability, delivering scalable capabilities for engineering teams.

Responsibilities include automating infrastructure with Terraform and AWS CDK, deploying production LLM workloads, and ensuring cost efficiency,

Qualifications

• 5+ years in software engineering, with 1+ year delivering LLM/actor apps in production.
• Cloud/platform/SRE experience with production systems.
• Hands-on AWS and other enterprise clouds experience; migrate skills to AWS is valued.
• IaC, containerized workloads, and CI/CD with Terraform, AWS CDK, Docker, ECS, EKS.
• Hands-on production LLM/AI workloads using models APIs and tools.
• Distributed systems with async processing, state, retries, idempotency, resilience.
• Observability, incident response, cost management, and security practices.
• Strong analytical, troubleshooting, communication, and collaboration skills.

Responsibilities

• Design, build, and operate secure, scalable AI platforms on AWS, applying patterns from other 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 workloads using Amazon Bedrock and related AWS services.
• Build resilient distributed systems with asynchronous processing, durable state, retries, idempotency, and recovery.
• Own agent-runtime reliability, including scaling, performance, observability, SLOs, incident response, pause/resume, and cost optimization.
• Implement identity, encryption, secrets management, and auditable access controls.
• Govern model access, quotas, provider onboarding, evaluation, and lifecycle controls.
• Partner with engineering, architecture, security, product, and business teams to establish reusable standards.

Skills

Cloud architecture

Security best practices

Observability

Incident response

Cost management

Collaboration

Tools

Terraform

AWS CDK

Docker

ECS

EKS

Job description

HedgeServ Corporation in the United States is seeking a Senior AI Platform and Runtime Engineer to design, build, and run HedgeServ’s shared AWS platform for AI agents and applications. You will own runtime infrastructure, identity, security, model access, deployment, and reliability, delivering scalable capabilities for engineering teams.

Responsibilities include automating infrastructure with Terraform and AWS CDK, deploying production LLM workloads, and ensuring cost efficiency,