Ratneshwaran Maheswaran

AI Researcher · UCL Centre for Artificial Intelligence

I am an AI researcher at the UCL Centre for Artificial Intelligence, where I build trustworthy AI systems for healthcare and science. My current work develops multilingual mental-health conversational agents with Freedom from Torture, combining agentic AI, clinical NLP, and safety evaluation.

Previously, I worked at the Secrier Lab at the UCL Genetics Institute, benchmarking foundation models (scBERT, scGPT, Geneformer, LangCell) for zero-shot cell annotation across cancer datasets. I hold a BEng in Electronic and Computer Engineering from the University of Nottingham, where I received the Vice-Chancellor's Medal (top 0.1%), and I am currently completing an MSc in AI for Biomedicine and Healthcare at UCL.

My research interests lie in AI safety, AI governance, agentic AI, foundation models, and NLP, with applications to mental health, clinical decision support, and computational biology.

News

Apr 2026 Teaching Assistant for COMP0190 (AI for Domain Specific Applications) at UCL.
Oct 2025 Joined the UCL Centre for AI as an Agentic AI Researcher, working on mental-health conversational agents with Freedom from Torture.
Sep 2025 Completed work at Secrier Lab on zero-shot cell annotation with foundation models; pre-print in preparation for 2026.
2024 Awarded the Vice-Chancellor's Medal at the University of Nottingham (top 0.1%) for academic, authorial, and leadership contributions.
2024 Began MSc in Artificial Intelligence for Biomedicine and Healthcare at UCL.

Research Interests

AI safety & governance — evaluation, alignment, and policy considerations for high-stakes AI systems.
Agentic AI & foundation models — reasoning, planning, and tool use with LLM-based agents.
Clinical NLP & healthcare AI — trauma-informed conversational agents; clinical decision support.
Computational biology — single-cell genomics, zero-shot cell annotation, cross-dataset generalisation.

Selected Projects

Grounded by Design: multilingual mental-health conversational agents.

R. Maheswaran. In collaboration with Freedom from Torture · UCL Centre for AI, 2026.

Trauma-informed, culturally sensitive agentic systems with evidence-based therapeutic strategies and safe, interpretable reasoning workflows.
LitAgent: an AI agent for automated literature review.

R. Maheswaran. Open-source system, 2025.

LangGraph-driven multi-agent system across arXiv and PubMed with Crossref metadata enrichment. Structured synthesis, gap analysis, and multi-format output (Markdown, JSON, CSV) via CLI and REST API, with a React/Vite frontend.
Enhancing aspect-based sentiment analysis with adversarial BERT.

R. Maheswaran. BEng Dissertation, University of Nottingham, 2025.

Improved BERT for aspect extraction, sentiment classification, and review comprehension by combining adversarial training with P-SUM/H-SUM, surpassing prior state-of-the-art in domain-specific NLP.
Zero-shot cell annotation with foundation models.

R. Maheswaran, M. Secrier. Pre-print in preparation, 2026.

Zero-shot pipelines for single-cell RNA-seq analysis across ovarian, prostate, kidney, and pancreas cancer datasets. Benchmarking of scBERT, scGPT, Geneformer, and LangCell with Accuracy, F1, AUROC, AUPRC; UMAP-based evaluation of generalisation and batch effects.
AI College Assistance — personalised counselling for international applicants.

R. Maheswaran. Full-stack system (React / FastAPI / PostgreSQL / GPT-4), 2025.

AI-driven counselling platform for students applying to UK, US, and Australian universities: essay feedback, timelines, portfolio builder, and a chatbot for personalised guidance.
Python Simplified.

R. Maheswaran. Apple Books, 2020.

Introductory Python textbook; over 30,000 copies distributed to underprivileged students.

Experience

2026–: Teaching Assistant, COMP0190. UCL Centre for AI. AI for Domain Specific Applications Project.
2025–: Agentic AI Researcher. UCL Centre for AI, in collaboration with Freedom from Torture. Multilingual mental-health conversational agents.
2025: AI & Genomics Researcher. Secrier Lab, UCL Genetics Institute. Benchmarking foundation models on single-cell RNA-seq.
2022–24: President, OPAD. Open-Source Assistive Devices, University of Nottingham. Led 12+ student-led medical-device projects; secured £1,500 in grants.
2020–23: Founder & CEO, 40seconds.org (Ratneshwaran Foundation). Non-profit on youth mental health and human rights; 120+ volunteers across 19 countries.

Education

2024–: MSc, Artificial Intelligence for Biomedicine and Healthcare. University College London. Predicted: Distinction.
2021–24: BEng (Hons), Electronic and Computer Engineering. University of Nottingham.

Teaching

COMP0190 — AI for Domain Specific Applications Project, UCL (MSc). Teaching Assistant, 2026–present.
Peer mentoring & OPAD project supervision, University of Nottingham, 2022–24.

Honours & Awards

Vice-Chancellor's Medal, University of Nottingham (2024) — top 0.1%, for contributions as author, philanthropist, and student leader.
EEE Undergraduate Studies Award, University of Nottingham (2024).
Nottingham Advantage Awards — Student Leader (2024); OPAD & Peer Mentor (2023).
Union Prize & Student Representative of the Year, University of Nottingham (2022).
Top 6 Teen Heroes, India (2021).
Invited speaker — World Summit AI, TEDx, university conferences.

Contact

The best way to reach me is by email at ratneshwaran.maheswaran.21@ucl.ac.uk. I'm always happy to hear from students, collaborators, and anyone working on trustworthy AI for healthcare.