AI Developer (Intern) at Narrates Limited

Assisted on RAG prototypes using LLMs and vector DBs for context-aware internal search.

Automation Engineer / NLP Specialist at Narrates Limited

Built automations for ingestion, retrieval, and inference; cut manual effort and latency. Tuned prompts and retrieval logic to boost recall and precision.

Senior ML Engineer at Digital Hero

Built RAG pipelines with LLMs + vector DBs (FAISS/Pinecone) and hybrid retrieval/ reranking; improved accuracy and grounding. Orchestrated eight workflows for ingestion/embeddings/retrieval/inference with retrievers/alerts, reducing manual ops and latency. Shipped NLP features (NER, intent, summarization) and tuned prompts/queries to boost recall and precision.