Lead AWS DevOps Engineer ? GenAI (No C2C)

• Contribute to the architecture, design, and production deployment of enterprise-scale software releases using generative AI systems, including LLM orchestration, agent/skill creation, retrieval-augmented generation, evaluation, and operational monitoring.
  
• Design and implement modular AI agents that connect to our core systems, and build clean abstractions that let non-technical users leverage these agents in useful workflows without writing code.
  
• Build automation that streamlines release operations, operational reporting, and engineering workflows for generative AI-enabled systems.
  
• Build and deploy containerized services and automation?packaging applications as Docker images, authoring Helm charts, and deploying to Kubernetes?and build and maintain the CI/CD pipelines (GitLab CI) that automate build, test, and release.
  
• Build and maintain dashboards and reports that provide ongoing visibility into release health, model and system performance, and operational metrics for deployed GenAI solutions.
  
• Build observability capabilities through dashboards, monitoring, alerting, tracing, and operational telemetry.
  
• Troubleshoot complex production issues across applications, cloud infrastructure, Kubernetes, APIs, distributed systems, and enterprise integrations.
  
• Provide technical guidance by mentoring junior engineers and contributing to technology decisions within the team.
  
• Apply and help improve GenAI engineering standards, reference architectures, and guardrails that ensure scalability, security, cost efficiency, and responsible AI use.
  
• Contribute reusable templates, patterns, and documentation that accelerate the team's ability to deliver.
  
• Develop generative AI-enabled software designs and improvements that enhance existing systems and processes.
  
• Produce clear technical documentation and architecture descriptions for internal and external stakeholders.
  
• Collaborate closely with Product Management, Platform Engineering, SRE, Security, UX, and engineering teams to deliver scalable, secure, and reliable software solutions.
  
• Also responsible for other duties/projects as assigned by business management as needed.
  
• 
  

Requirements

Required Experience

• 7+ years of experience in full-stack development, SQL, and ETL.
  
• 7+ years of experience with CI/CD.
  
• 5+ years of IT Cloud experience.
  
• 4+ years of technical engineering experience.
  
• Strong hands-on experience with AWS and DevOps.
  
• Experience developing and deploying Generative AI/LLM solutions.
  
• Experience with LLM orchestration, AI agents/skills, RAG, evaluation, and operational monitoring.