We are hiring a Senior AI Engineer to build LLM-based software solution prototypes for enterprise use cases. You will work closely with the Solutions Architect and Research Scientist to translate research ideas into robust prototypes, validate feasibility through experiments, and mature successful prototypes into production-ready components.

This role is hands-on: you will design, implement, evaluate, and deploy LLM-centric systems, including retrieval-augmented generation (RAG), agentic workflows, tool/function calling, and model evaluation/monitoring pipelines. You will also leverage modern AI coding assistants to accelerate development while maintaining strong engineering rigor.

• Build end-to-end LLM-powered prototypes: from problem framing and technical design to implementation and demo delivery.
• Implement and optimize RAG pipelines (chunking, embedding, retrieval, reranking), prompt/context engineering, and tool-use / function-calling flows.
• Design and run experiments to compare approaches (prompting vs fine-tuning, RAG variants, routing, guardrails), and present results clearly.
• Design, run, and maintain evaluation plans for LLM applications using the latest tools and frameworks.
• Develop scalable backend services and APIs to support prototypes (e.g., FastAPI), integrate with internal systems and data sources.
• Use AI-assisted coding tools (e.g., Claude Code / Codex) effectively for scaffolding, refactoring, test generation, and documentation, while ensuring correctness through reviews and testing.
• Collaborate with product/business stakeholders to define success criteria, scope prototypes, and deliver iterative improvements.
• Provide technical leadership: code reviews, architecture guidance, and contributing to engineering best practices.