Design and develop GenAI-powered solutions using Large Language Models (LLMs)

Build Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge systems

Implement agentic workflows using LangChain and LangGraph

Develop and optimise prompt engineering, tool calling, and memory management

Integrate LLMs with voice pipelines (STT, TTS, call analytics)

Fine-tune or adapt models using LoRA / PEFT techniques when required

Work closely with product, data, and backend teams to translate business use-cases into AI solutions

Deploy models and pipelines to production with performance, latency, and cost optimisation

Monitor and improve model quality, hallucinations, and response accuracy

Ensure AI safety, data privacy, and compliance best practices