Solution Architect – AI, MCP & Cloud Engineering

Role Overview We are seeking a hands-on Solution Architect to lead the design and technical direction of AI-driven, MCP-enabled solutions and cloud-native platforms. The ideal candidate will combine strong software architecture expertise with practical experience in AI application development, agentic systems, cloud engineering, and modern software development practices. The candidate will take ownership of solution architecture, establish engineering standards, and guide teams in building scalable, secure, reliable, and maintainable enterprise solutions. Key Responsibilities Own end-to-end solution architecture, technical design, and implementation strategy for AI-driven applications and platforms. Design and develop AI-enabled workflows, agentic applications, and integrations using the Model Context Protocol (MCP). Define architecture patterns for tool integration, context management, API orchestration, and interaction between AI models and enterprise systems. Lead cloud architecture and implementation across Microsoft Azure, with growing support for Google Cloud Platform (GCP). Establish best practices for application security, scalability, reliability, observability, and maintainability. Evaluate architectural trade-offs, technology choices, and build-versus-buy decisions. Guide engineering teams through design reviews, code reviews, technical problem-solving, and implementation. Promote AI-assisted software development and modern engineering practices across the SDLC. Collaborate with product, engineering, DevOps, security, and quality teams to ensure successful delivery. Support compliance-driven architecture requirements, including FedRAMP-related considerations where applicable. Required Skills & Experience Strong experience in solution architecture, software engineering, and distributed systems. Hands-on expertise in designing cloud-native applications and enterprise integrations. Experience with Microsoft Azure and familiarity with cloud security, identity, networking, monitoring, and deployment services. Knowledge of GCP or the ability to design solutions across multiple cloud environments. Practical understanding of LLM-powered applications, AI agents, tool calling, and MCP-based integrations. Strong understanding of APIs, microservices, event-driven architecture, data flows, and system integration. Experience with CI/CD, infrastructure automation, observability, and secure development practices. Ability to lead technical teams while remaining hands-on with critical design and implementation challenges. Preferred Qualifications Experience building production-grade AI applications or agentic platforms. Exposure to FedRAMP or other regulated cloud environments. Experience with Kubernetes, containers, infrastructure as code, and automated deployment. Knowledge of AI evaluation, guardrails, access controls, and responsible AI engineering. Success Criteria Clear technical ownership from architecture through implementation. Scalable and secure AI-enabled solutions delivered using sound engineering practices. Effective adoption of MCP and AI development patterns where appropriate. Strong alignment across architecture, development, performance, security, and quality engineering.