• Analyze, design, program, debug, test, implement, deploy, and support software enhancements and new applications using Generative AI technologies • Contribute to the development and production deployment of GenAI-enabled applications, including LLM-powered workflows, RAG pipelines, and AI-driven user experiences • Support SDLC documentation across all phases, with a focus on deployment, evaluation, observability, safety, and monitoring • Interact with users to define requirements and support applications in production • Develop and modify application modules, including GenAI components • Build prompt workflows, retrieval layers, APIs, and cloud services • Troubleshoot production issues, including latency, hallucinations, and errors • Provide Level II production support for deployed systems • Design components, including LLM integrations and RAG pipelines • Implement CI/CD pipelines, containerization, and release processes • Develop RAG pipelines with embeddings, chunking, and vector search • Apply prompt engineering techniques, including few-shot prompting and structured outputs • Evaluate models for accuracy, relevance, and hallucination risk • Implement safety guardrails, including PII protection and prompt-injection defense • Execute testing, including unit, integration, and GenAI evaluation testing • Monitor production systems for latency, cost, usage, and errors • Support incident management with fallback and recovery strategies

• Manage multiple AWS accounts with tools like AWS Control Tower and Terraform • You will deploy and debug cloud stacks, educating teams on new cloud projects, and ensuring the security of the cloud infrastructure • As a SRE, you can identify the most optimal cloud-based solutions for our internal users, and maintain cloud infrastructures following industry leading practices and company security policies • This is a 24/7 on-call position with a rotation schedule

• Lead the standardization of application deployments, containerization, and release processes • Design and implement consistent, repeatable deployment pipelines • Containerize applications using Docker and orchestration platforms like ECS or Kubernetes • Establish shared CI/CD frameworks • Create tooling and documentation that empowers engineering teams to ship reliably • Define best practices and golden paths for deployment

• Design, evolve, and operate scalable, resilient cloud environments; • Drive the evolution of SRE practices, observability, reliability, and automation; • Work with infrastructure as code and GitOps-based pipelines; • Support engineering teams in adopting best practices for delivery and operations; • Create automations to reduce manual work and increase operational efficiency; • Participate in incident analysis, troubleshooting, and continuous improvement; • Contribute to platform standards, tools, and capabilities.