Principal AI Researcher · Interpretability · Knowledge Distillation · World Models · AI × Science
Currently Founding Principal AI Researcher at Erdős AI Lab, working on mechanistic interpretability, knowledge distillation, world models, and AI × Science.
Fine-tuning 0.5B-7B LLMs with QLoRA and 4/8-bit quantization, deployed on Jetson Nano. Active threads: diffusion language models and aggressive compression (PTQ/QAT/AWQ/GPTQ/pruning) feeding Indic text generation.
Mechanistic interpretability with SAEs: attention circuits, feature attribution, and the full SAE gallery from the KD paper. See the gallery.
Benchmark of 18 vision architectures on PCOS ultrasound. A hybrid CNN-ViT hit 99.81%; a three-stage dedup pipeline cleaned 70% of the public dataset. Read more.
Four results on one A100: a 1 µs chignolin fold, titin I27 force-pulling, an 8-protein ESMFold sweep in 12.9 s, and ESMFold calibration. Read more.
Real-time computer vision for object detection and autonomous navigation in complex environments.
Teleoperated robotic arm with low-latency control for precise manipulation in semi-structured environments.
Precision parametric CAD engine with machine-readable proof of correctness attached to every exported file.
Knowledge distillation, representation learning, world models, and mechanistic interpretability. EF-backed, incubated at IIT Bombay. Read more.
Air-gapped agentic RAG, document intelligence, an internal MCP server, gesture recognition, and supply-chain AI for aerospace. Read more.
Department-led research across language models, autonomous drones, humanoid robotics, and medical AI. See all DSU work.
Built a portfolio of 24 Python projects: data visualisations, Tkinter GUIs, and an end-to-end chatbot, with project management on GitHub and Notion.
Student-founded lab on knowledge distillation, world models, and frontier AI. Funded and trusted by Entrepreneurs First (EF); incubated at IIT Bombay. Read more.
Leading tech initiatives for entrepreneurial ventures: overseeing infrastructure and bridging business ideas with technical solutions.
Core Committee, Institution of Engineering and Technology (IET) DSU chapter and the Roboverse student community; ran 10+ tech talks, workshops, and hackathons bridging theory with practice in AI and robotics.
Executive Committee, IEEE RAS and IEEE CIS at DSU. 50+ workshops, talks, and hackathons. RAS & CIS Exceptional Volunteering Award, 2025, given to the top 10% of undergraduate researchers at the university.
NVIDIA Deep Learning Institute course on transformer fundamentals: attention, tokenization, and downstream NLP tasks.
AWS Cloud Practitioner EssentialsFoundational AWS knowledge: core services, security, billing, and the shared-responsibility model.
AWS Technical EssentialsHands-on coverage of compute, storage, databases, networking, and security on AWS.
Microsoft Learn: Benefits of Cloud ArchitectureCloud-architecture fundamentals: design principles, trade-offs, and Azure mappings.
Kaggle: Intro to Machine LearningKaggle's foundational ML course: model fitting, evaluation, and validation on tabular problems.
Altair RapidMiner Certified Data Science ProfessionalProfessional certification covering end-to-end data-science workflows on the Altair RapidMiner platform.
Artificial Intelligence and Robotics Engineering (2023-2027). Designed the LLM Engineering curriculum and lab manuals featured on the university website.
Inside Erdős AI Lab, the day-to-day research stack: knowledge distillation, mechanistic interpretability (SAEs), world models, and protein structure prediction. Includes a KD paper and the full SAE experiment gallery.
AI × Bio: Protein FoldingFour experiments on real proteins, all on one A100: a 1 µs chignolin fold, titin I27 force-pulling, an 8-protein ESMFold sweep, and ESMFold calibration. Reproducible from the linked code.
India AI Impact Summit 2026Representing DSU at India's premier AI conference in New Delhi, engaging with 250+ companies, and presenting research on LLM architecture, medical AI, and autonomous drones.
SAE Experiments: KD paperToy-model validation of the KD minimum-width theorem plus three real-LM trials on Pythia-410M (24 layers × 6 checkpoints, full sparsity sweep) published on Hugging Face.
Language Modeling ExperimentationFine-tuning Qwen 0.5B-7B for low-resource Indic languages; deploying Gemma 3 1B on Jetson Nano. Diffusion-LM and compression threads now live.
Medical AI: PCOS DetectionBenchmark of 18 vision models on PCOS ultrasound. A hybrid CNN-ViT hit 99.81%. A three-stage dedup pipeline cleaned 70% of the public dataset.
I'm always open to discussing research, engineering challenges, or just chatting about the future of AI.