Architect end-to-end AI architectures for LLM-powered applications, RAG, agentic workflows, orchestration frameworks, APIs, and enterprise data integration
Define reusable architecture patterns, reference implementations, and deployment approaches that accelerate delivery across teams
Enable secure, resilient, observable, and cost-effective AI services across cloud-native environments
Embed responsible AI, security, privacy, auditability, and regulatory controls into solution designs
Establish best practices for prompt engineering, evaluation, testing, observability, model lifecycle management, and production readiness
Review architectures and code, optimize performance and reliability, and support experiments that validate business value
Serve as a trusted advisor to product, engineering, data, risk, and architecture stakeholders
Mentor engineers and technical leads on AI architecture, emerging technologies, and delivery practices
Drive alignment across teams while balancing innovation, governance, and pragmatic execution
Requirements
10+ years in software engineering, distributed systems, or application architecture
Demonstrated Generative AI solutions in production
Expertise with LLMs, RAG, agentic AI, LangChain /LangGraph or similar frameworks, vector databases, APIs, microservices, cloud-native platforms, and Kubernetes/EKS