Rahul Summan

Ai Solutions Engineer @Nile

Edinburgh, GB

Lead engineer on language model–based systems, working with both large and small language models. Responsible for fine-tuning models for targeted applications, building agent-based systems using LangChain, and deploying scalable solutions on AWS (Lambda, Fargate). Overseeing technical direction and implementation across the LLM stack — from model optimization to deployment and orchestration — to deliver production-grade ML services. Current focus includes retrieval-augmented generation (RAG) and building internal tools powered by LLMs.