SAC Planning

Job Summary

The Technology Architect (ETE124) will architect and oversee end to end solutions that combine Generative AI, SAP SAC Analytics, Prompt Engineering, Agentic AI, and Context Engineering within a hybrid work model. This role is responsible for governing scalable architectures, ensuring robust delivery practices, and maintaining strong alignment with customer outcomes across data driven and AI enhanced applications.

Responsibilities

• Lead end to end architecture blueprints integrating Generative AI services, SAP SAC Analytics models, Prompt Engineering workflows, Agentic AI capabilities, and Context Engineering patterns to deliver secure and scalable enterprise solutions
• Establish reference architectures and standards to support consistent adoption of Generative AI, SAP SAC Analytics, and related AI accelerators, ensuring alignment with enterprise strategy and compliance requirements
• Work with product owners and business stakeholders to convert complex analytics and AI requirements into clear solution designs, optimizing data flows, latency, and end user experience quality
• Support engineering teams in building context aware pipelines that leverage both structured and unstructured data, ensuring Context Engineering practices increase relevance, precision, and explainability of AI outcomes
• Design reusable Prompt Engineering patterns and guardrails to enable safe and predictable use of large language models, minimizing experimentation risk and improving maintainability
• Assess and choose cloud native and on premises components for SAP SAC Analytics and Generative AI workloads, balancing cost, performance, resilience, and regulatory obligations for global enterprise delivery
• Manage non functional architecture requirements including performance, reliability, observability, security, and privacy for AI centric and analytics centric solutions across development, test, and production environments
• Partner with data engineering and integration teams to define resilient ingestion, transformation, and semantic modeling layers that power SAP SAC Analytics dashboards and AI driven insights with high data quality
• Set up architecture review checkpoints, document architectural decisions, and track technical debt to keep AI and analytics platforms extensible, maintainable, and ready for future innovation cycles
• Mentor solution engineers and analysts on best practices for Prompt Engineering, Agentic AI orchestration, context management, and SAP SAC Analytics modeling to strengthen internal capability
• Run feasibility assessments and proof of value experiments to demonstrate how Generative AI and Agentic AI solutions improve decision making, productivity, and customer satisfaction for both clients and internal users
• Collaborate with security and risk teams to implement responsible AI principles, access controls, data protection mechanisms, and monitoring capabilities across Generative AI and analytics solutions
• Align technology roadmaps with sustainability and social impact objectives by promoting architectures that improve operational efficiency, reduce wasteful processing, and democratize access to trustworthy insights for diverse stakeholders

Qualifications

• 15 to 18 years of progressive experience in architecture or senior technical design roles, including a strong track record delivering complex analytics and AI enabled solutions for large enterprises
• Hands on expertise in Generative AI technologies, including large language models, embeddings, retrieval systems, and prompt optimization, with practical experience delivering Prompt Engineering and Agentic AI solutions
• Advanced proficiency in SAP SAC Analytics, including model design, data actions, planning scenarios, visualization standards, and integration with upstream data platforms and downstream enterprise applications
• Strong capabilities in Context Engineering, including context store design, session management, grounding techniques, and strategies to reduce hallucination risks in AI responses across multiple use cases
• Solid understanding of software engineering practices, including microservice architectures, event driven patterns, API design, version control, automated testing, and observability designed for AI centric workloads
• Domain experience across enterprise analytics and digital transformation initiatives such as finance analytics, operations analytics, customer insights, or supply chain analytics, where AI augmented decisioning provides measurable value
• Good to have exposure to industry specific regulations and practices in areas such as banking, retail, manufacturing, or healthcare analytics to align AI and analytics solutions with domain expectations and controls
• Primary work within a hybrid work model combining on site collaboration with remote delivery, while maintaining high standards of communication, documentation quality, and coordination across distributed teams
• Day shift work environment, with flexibility to collaborate across time zones through planned overlap windows and asynchronous communication mechanisms when required
• No regular travel required; however, limited short visits may be possible if agreed later based on specific project needs and organizational guidelines