





Senior, niche LLM principal role at a lesser-known firm limits applicant density.
Specialized LLM production, RAG, vector DB and enterprise/SAP integration require domain-specific experience.
Explicit 10+ years, proven LLM production leadership and specific tech requirements create strict filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own architecture and end-to-end delivery of AI-based applications and platforms integrating LLMs, AI agents, and automation in enterprise subscription billing, primarily around SAP.
Lead the AI engineering team including setting direction, mentoring, managing performance, and ensuring timely, quality delivery.
Design and build scalable LAG, retrieval, memory, vector-database systems; develop backend services in Python and Java; handle prompt engineering and multi-agent orchestration.
10+ years in software engineering with recent experience deploying LLM-based systems in production.
Proven experience leading and managing engineering teams with ownership of team performance and growth.
Strong hands-on skills in Python and backend Java; experience with LLM frameworks like LangChain, LangGraph, AutoGen, or LlamaIndex.
Experience with RAG architectures, prompt engineering, vector databases (FAISS, Pinecone, Chroma, pgvector), enterprise APIs, and at least one cloud platform (AWS, Azure, or GCP).
Senior engineer with substantial ownership in AI/LLM system architecture and production deployments in enterprise contexts, especially subscription and billing platforms.
Experienced engineering leader comfortable balancing hands-on coding with people management and strategic technical direction.
Skilled in scaling AI systems involving complex prompt engineering, multi-agent orchestration, and integration with secure enterprise and SAP environments.