About the Role Join the team behind our powerful internal generative AI platform leveraging multi-vendor LLMs (e.g., GPT‑4, Claude, Sonic, Haiku). You’ll build robust, secure, enterprise-grade tools that empower employees across business units—creating custom solutions, reusable frameworks, and end-to-end greenfield applications with AI at their core. What You’ll Do • Build scalable multi-model chat and data-extraction systems across vendors. • Design and deliver AI-driven frameworks that accelerate innovation and reduce time-to-market. • Develop full-stack applications using Python, TypeScript/Next.js, and AI-first development tools. • Use Terraform to provision and manage the necessary infrastructure. • Integrate LLM APIs, including GPT‑4 and Claude, and develop model components using generative AI frameworks like LangChain and vector databases • Prototype and build AI-driven applications (e.g., Claude, Sonic, Haiku) with modern data science techniques. • Implement RAG architectures and vector DBs to support retrieval-augmented systems • Employ Docker/containerized development and produce JS-based front ends via React/Next on AI-driven apps. Must-Have Qualifications • 2+ years as a Generative AI Engineer (distinct from traditional ML or full-stack roles), with recent experience in AI-first development. • 5+ years total in full-stack development using Python and JavaScript • Proven track record integrating LLM APIs (e.g., GPT‑4, Claude) in production. • Hands-on with generative AI frameworks (e.g., LangChain, vector DBs) • Experienced in RAG architecture and vector database integration (e.g., Pinecone, FAISS) • Skilled in containerization (Docker) and infrastructure management (Terraform). • Solid front-end development experience with React/Next.js or similar frameworks. Nice to Have • Familiarity with graph or database-backed RAG integrations (e.g., using knowledge graph DBs). • Prior work on internal, enterprise-grade platforms or AI-driven tooling.