Generative AI Engineer

Role Summary
We are looking for a GenAI Engineer to design, build and scale production-ready Generative AI solutions that solve enterprise business problems.
The role will focus on LLM-powered applications such as copilots, conversational agents, document intelligence solutions, and AI-driven automation integrated with enterprise systems, including SAP S/4HANA.
The engineer will work with product, SAP, backend engineering, and cloud platform teams to deliver secure, compliant, cost-efficient, and reliable AI capabilities for business adoption.
What You Will Do
1. Build GenAI Solutions
Design, develop, and deploy GenAI applications using Azure OpenAI, AWS Bedrock, and Kiro.
Build enterprise copilots and AI agents using Microsoft Copilot Studio or similar low-code/pro-code frameworks.
Create RAG pipelines using vector search and enterprise knowledge sources to ground AI responses.
Apply prompt engineering techniques to improve response accuracy, consistency, and usability.
2. Integrate with Enterprise Systems
• Integrate GenAI capabilities with SAP S/4HANA using OData services, APIs, workflow triggers, and event-driven patterns.
• Build secure API layers connecting AI services with ERP, CRM, and operational systems.
• Work with SAP functional and Basis teams to align AI touchpoints with business processes, authorizations, and data governance needs.
3. Engineer for Scale, Quality and Governance
• Contribute to solution architecture, platform selection, cost optimization, security, and deployment decisions.
• Design evaluation approaches for LLM quality, hallucination risks, latency, cost, and user satisfaction.
• Set up monitoring for production AI applications using relevant cloud and observability tools.
• Apply responsible AI practices such as content filtering, guardrails, bias checks, and explainability where required.
• Maintain model, prompt, and version-control discipline to support production stability.
Skills and Experience Required
• 5+ years of software engineering experience, including hands-on delivery of AI, LLM, or applied ML solutions in production environments.
• Strong Python programming skills, with working knowledge of TypeScript, Java, or Node.js as an advantage.
• Hands-on experience with Azure OpenAI Service, AWS Bedrock, or equivalent LLM platforms.
• Practical experience building copilots, AI agents, or intelligent automation using Copilot Studio, Azure AI Studio, LangChain, LlamaIndex, or equivalent frameworks.
• Strong understanding of RAG design, vector embeddings, chunking strategies, and retrieval optimization.
• Experience integrating systems using REST APIs, OData, GraphQL, or event-driven architectures.
• Understanding of cloud deployment, Docker, Kubernetes, and CI/CD pipelines for AI workloads.
• Good understanding of enterprise security patterns including OAuth 2.0, managed identities, RBAC, secret management, and data residency considerations.
Preferred / Good to Have
• Experience integrating AI services with SAP S/4HANA.
• Knowledge of SAP BTP, SAP Integration Suite, SAP AI Core, or SAP Joule.
• Familiarity with Azure AI Search, OpenSearch, Pinecone, LangSmith, Azure Monitor, or AWS CloudWatch.
• Experience with model evaluation, guardrails, and responsible AI implementation in enterprise settings.
Candidate Attributes
• Customer-focused: understands business use cases and builds solutions that solve measurable problems.
• Challenger mindset: brings new ideas, learns quickly, and improves existing ways of working.
• Committed: owns delivery, follows through, and supports production-quality engineering standards.
• Clear communicator: explains complex AI concepts simply to technical and business stakeholders. • Connected collaborator: works effectively across product, SAP, platform, security, and business teams.
Success Measures
• Production-ready AI solutions delivered securely and reliably.
• Measurable business value through automation, productivity, or better decision support.
• High-quality AI responses supported by testing, monitoring, and continuous improvement.
• Strong stakeholder adoption and collaboration across business and engineering teams.

Work arrangement
No