Research Interests
AI Safety & Alignment ·
Natural Language Processing (NLP) ·
Mechanistic Interpretability ·
Large Language Models (LLMs) ·
Geometric Deep Learning ·
Explainable & Trustworthy AI ·
AI Deception Detection ·
Cross-cultural & Multilingual AI ·
Privacy-Preserving Federated Learning ·
Healthcare NLP
Core Research: Belief Vector Field & Geometric Alignment
My primary research develops information-geometric frameworks to measure how LLMs encode, propagate, and transform beliefs across transformer layers — and how alignment (DPO/RLHF), fine-tuning, and cultural merging alter that internal geometry.
Core finding: torsional geometry provides the most statistically significant separation (highest Cohen's d effect size) between safe and harmful prompts across SFT & DPO model variants.
Models: LLaMA-3.2, OLMo-7B, Gemma-2, Mistral-7B, Zephyr-7B, Qwen3 |
Datasets: LITMUS, HarmfulQA, hh-rlhf |
Metrics: 17 geometric metrics (torsion, spectral curvature, thermodynamic length, DTW)
Semantic Helix of LLMs (nDNA) — Cross-cultural & Multilingual AI
Unifies fine-tuning, alignment, distillation, and model merging as measurable deformations of the same depth-wise semantic flow via spectral curvature κℓ and thermodynamic length ℒℓ. Investigates epistemic inheritance in merged LLMs — emergent cultural “neural DNA” across African, Latin American, South Asian, East Asian, Arabic, European, and Pacific Islander cultures.
Research & Work Experience
Nalhati Government Polytechnic College (Govt. of West Bengal), India
Teaching ML, Deep Learning, IoT, Python, and Java. Project supervisor for 50+ final-year students on AI, NLP, Agentic AI, and Empathetic Chatbot projects. Administrative HoD responsibilities. Active research on AI Safety & Alignment (GRAFT/MENTIS), Semantic Helix of LLMs (nDNA), Cultural LLMs, and Neural Robustness.
Wipro Limited & IBM Research (Joint Project), Bangalore, India
Led a team of 5 to build a conversational chatbot removing query ambiguities. Implemented 50+ custom intents, entities, and dialog flows with IBM Watson. Impact: 0.3 million users worldwide. Tools: DialogFlow, IBM Cloud, NodeJS.
BirlaSoft · Johnson & Johnson R&D, New Delhi, India
Built medical search engine using SciBERT and SciSpacy NLP pipeline for healthcare queries. Impact: 0.1 million+ J&J product users. Tools: Python, Word2Vec, SciSpacy, Fuzzy Search, Flask.
Indian Institute of Technology (IIT) Kanpur, Computer Science Dept., India
Developed a secure threat management system for academic institutions. Researched cyber-security defences against integrity, confidentiality, and non-repudiation attacks. Tools: Python, Drupal, Django.
Infosys Technologies Limited, Chennai, India
Applied Edit Distance and Needleman-Wunsch algorithms on DNA sequences (FASTQ) to identify gene insertions/deletions. Identified top 10 genes driving Multiple Myeloma blood cancer; implemented 3 research papers. Impact: biological hierarchy determination, drug design, life expectancy improvement.
Teaching Assistantships
BITS Pilani, India
TA for three graduate courses: NLP Applications [Winter 2023], Deep Learning [Fall 2021], Deep Reinforcement Learning [Spring 2021]. Responsibilities: webinar demonstrations, labs, quizzes, exam preparation, student mentoring. Honorarium: USD $2,513.11 across all three courses.
Education
M.Tech in Data Science & Engineering
Birla Institute of Technology and Science (BITS Pilani), Pilani, India — 2019–2021
GPA: 9.08/10 · Distinction · Top 5% out of 600
Courses: NLP, Machine Learning, Deep Learning, Data Science, Mathematics, Statistics, Data Mining, Big Data Systems
Dissertation: Collaborative Federated Learning (CFL) cloud system separating PHI/PII for privacy-preserving GPT-like systems (published SpringerNature)
B.Tech in Computer Science & Engineering
West Bengal University of Technology (WBUT), Kolkata, India — 2006–2010
GPA: 8.49/10 · Top 5% out of 70
Courses: Mathematics, Statistics, Algorithms, AI, Probability, Data Structures, Programming
Technical Skills
AI Safety:
Belief Change under AI Alignment, Mechanistic Interpretability, Model & Activation Steering, Recursive Self-Improvement Risks, LLM Deception, Manipulation & Sycophancy, Bias Mitigation & AI Misalignment, Catastrophic Risk Reduction in Frontier Models, Safety-Relevant Behavioral Evaluation, Belief & Knowledge Editing, Explainable & Trustworthy AI (XAI)
NLP:
Foundation Models, LLM Alignment, AI Agents, Conversational AI Systems, Generative AI, Fine-tuning via HuggingFace, Hybrid & Multi-hop Retrieval-Augmented Generation (RAG)
LLMs (hands-on):
DeepSeek, GPT, LLaMA, Gemma, Mistral, Qwen, OLMo — base & instruct variants; model fine-tuning, reasoning, NeuroSymbolic AI, ethics & trustworthiness, evaluation & benchmarking
Deep Learning:
Transformer, GPT, Autoregressive Generative Models, CNN, RNN, Neural Networks
ML & Data Science:
Text & Multimodal Data curation, Regression, Classification, Clustering, Tree-Based Algorithms, Bagging, Boosting
Programming:
Python, Java, C, Objective-C
Frameworks & Tools:
PyTorch, LlamaIndex, LangChain, Scikit-learn, NumPy, Pandas, NLTK, SpaCy, TensorFlow, Keras, Flask, NodeJS, Docker, Kubernetes, Git, PostgreSQL, MySQL
Cloud:
AWS (EC2), Azure, IBM Cloud, Watson ML; inference deployment systems
Domains:
Cancer Genomics, Bioinformatics, Healthcare AI, Real Estate, Finance & Banking
