AI/GenAI Engineering & Architecture

• Design and build scalable LLM-powered applications, intelligent assistants, and AI copilots aligned to business transformation goals.
• Architect and implement advanced RAG pipelines, knowledge retrieval systems, and agentic / multi-agent workflows using commercial and open-source models.
• Write clean, well-tested, production-grade code across the full AI application stack - from data ingestion and embedding pipelines to orchestration logic, API layers, and evaluation harnesses.
• Integrate vector databases, semantic search, prompt orchestration, tool/function calling, memory, and context-aware reasoning into enterprise-grade solutions.
• Optimize prompts, inference pipelines, and evaluation frameworks; contribute to fine-tuning, alignment, and model optimization efforts.
• Independently design scalable, AI-native application systems - moving quickly from ambiguity to working, deployable prototypes and iterating through execution.

SAP Ecosystem Integration

• Build agentic workflows on SAP AI Core and integrate LLM-based features into CAP /Fiori applications with strong coding standards and maintainability.
• Design and implement AI agents for enterprise domains - including formula explanation, computation assistance, and analytical workflows - using SAP AI Core and Python as the primary stack; CAP/Java as secondary.
• Contribute to the design of ontology-grounded agents that encode business rules, formula structures, and domain relationships as structured knowledge, enabling reliable agent reasoning beyond prompt-only approaches.
• Architect and deploy solutions on SAP BTP, with hands-on experience in multi-tenant SaaS patterns (MTX, service-manager, IAS/AMS).
• Knowledge of SAP Business Data Cloud (BDC) - including data products, HANA Data Lake, Delta Sharing, and the semantic layer - is a strong advantage.

Platform, LLMOps & Observability

• Establish and implement LLMOps practices covering deployment, monitoring, observability, governance, and guardrails - with hands-on implementation, not just design.
• Instrument OTEL tracing across microservice fleets and build Cloud Logging dashboards for cross-service visibility.
• Optimize latency, throughput, and cost efficiency - including HANA Cloud query optimization and AI Core inference cost management.
• Apply SRE principles in practice: monitoring, alerting, incident response, and root cause analysis.
• Build and own evaluation and benchmarking frameworks that measure AI system quality, reliability, and performance - including domain-specific test harnesses validating LLM outputs against known good results.

Research, Innovation & Collaboration

• Contribute to PoCs, accelerators, and reusable AI solution ; actively participate in innovation incubation.
• Support publication of technical white papers and assets; contribute to patent ideation where applicable.
• Partner with platform, data, product, and business teams to design robust, production-ready solutions.
  • Mentor junior engineers, conduct rigorous code reviews, and raise the engineering bar across the team.