CURRICULUM VITAE

Dilini Sumanapala

Dilini Sumanapala

Dilini Sumanapala

LLM powered applications consultant and engineer specialising in AI agents, AI enablement, conversational AI architecture, and production NLP systems.

LLM powered applications consultant and engineer specialising in AI agents, AI enablement, conversational AI architecture, and production NLP systems.

LLM powered applications consultant and engineer specialising in AI agents, AI enablement, conversational AI architecture, and production NLP systems.

Founder, Genverv Ltd.

London, UK

AI Agents · Conversation · NLP · AI Enablement

AI Agents · Conversation · NLP · AI Enablement

Skills

Skills

A practical stack for building, evaluating, and deploying agentic and language-driven systems.

AI Agents

RAG

LangChain

LangGraph

Rasa

Python

NLP

LlamaIndex

OpenAI Deployment

AWS

Haystack

Hugging Face

Experience

Experience

LLM Powered Applications Consultant and Engineer

LLM Powered Applications Consultant and Engineer

10.2023 – Present · London, UK

Lead Curriculum Architect — Conversational AI & Agents

Owns reference architectures and advanced agentic AI curriculum for LLM orchestration, tool integration, system boundaries, and maintainable enterprise assistant deployments.

Subject Matter Expert, LangChain / LangGraph AI Agents

Created production AI agent pipelines in Python using LangChain and LangGraph, including custom tools, AI control logic, OpenAI integration, and safeguards against hallucinations. Deployed live to more than 8,000 DataCamp subscribers.

Generative AI Engineer — RAG Applications

Built an LLM-powered patent chat prototype for biotech use-cases using LangChain, LlamaIndex, AWS Textract, OpenAI, Hugging Face, Streamlit, and Qdrant vector stores for small molecule patent PDFs.

Independent ML and NLP consulting

Independent ML and NLP consulting

04.2019 – 10.2023 · London, UK

Sentiment analysis

Analysed 60,000 tweets using Facebook’s RoBERTa algorithm to track brand sentiment and identify creative marketing opportunities.

Text similarity

Developed a Gensim tf-idf pipeline for document similarity hierarchies and content recommendation between fiction volumes.

Named entity recognition

Used SpaCy to extract people, organisations, places, events, and dates across 9,000 European Parliamentary documents.

Blicx recommendation simulator

Created a PyCaret and Streamlit machine-learning app to predict videogame recommendation likelihood and model future gaming habits.

Education

Education

PhD, Psychology (Cognitive Neuroscience)

2013 – 2017 · Bangor University, Wales, UK

Investigated MRI brain patterns involved in observational learning using machine learning.

Postdoctoral Researcher (Neuroscience)

2017 – 2019 · Birkbeck / UCL, London, UK

Managed delivery of a videogame-based maths and science learning intervention across 90 primary schools in England involving 6,500 pupils.

Publications

Publications

Sumanapala, D., Walbrin, J., Kirsch, L., & Cross, E. (2018). Neurodevelopmental perspectives on dance learning: Insights from early adolescence and young adulthood. Progress in Brain Research, 237, 243–277.

Kirsch, L., Diersch, N., Sumanapala, D., & Cross, E. (2018). Dance training shapes action perception and its neural implementation within the young and older adult brain. Neural Plasticity.