Build AI-powered features using LLMs, design RAG pipelines, and integrate generative AI into client products and internal tools. This is applied engineering: shipping features people use, with evaluation and cost control taken seriously.
Python. Practical experience with LLM APIs and prompt design. Understanding of RAG architecture including chunking, embeddings and retrieval quality. Ability to evaluate output rather than assume it is correct.
Design and build RAG pipelines. Integrate LLMs into products and internal tools. Build evaluation harnesses for model output. Manage inference cost and latency. Work with clients on AI feasibility and scoping.
Submit your application and we'll get back to you within 5–7 business days.
Apply for this positionCelestinfo is a technology company specializing in Data Engineering, AI/ML, Cloud Computing, and Enterprise Software Solutions.
Learn more →