Researching resource-efficient artificial intelligence and hardware acceleration — building open-source tools for AI, security, education and knowledge systems.
Doctoral research (NIT Goa) on hardware acceleration of Generative Adversarial Networks for FPGA-based edge devices — evolutionary and multifractal methods to stabilise training, and hardware-aware design for low-latency, low-power inference.
Multifractal Detrended Fluctuation Analysis embedded in the discriminator for stable, hardware-optimised synthetic image generation — without changing the core GAN architecture.
Genetic-algorithm-optimised generator with wavelet-based discrimination, synthesised on the AMD Kintex-7 KC705 with the lowest area footprint among compared implementations.
A 2D multifractal discriminator for fast synthetic-data generation, deployed on the Kintex-7 KC705 through the NNGen framework with verified hardware results.
Research and software are treated as one pipeline. Each paper is linked to its method, implementation and (where it exists) source code.
Some publications have no public code yet — those are listed as paper-only rather than inventing links. Verified implementations are shown with their exact repository.
Four flagship, pinned projects from the charudatta10 profile. The full project audit — automation, AI tooling, security, knowledge systems — lives on the work page.
A ~160-line minimalist LLM framework for Lua. Zero dependencies, zero vendor lock-in; agents, workflows and RAG in one file.
Static site with a client-only RAG chatbot over the founding figures of forensic science — WebLLM in the browser, no server, no API keys.
A composable, SPDX-compatible licensing framework — modular legal clauses instead of rewriting licenses, with monetisation built in.
Aggregated link hub — a curated, categorised collection of useful resources with custom link icons and fast setup.
Verified against ORCID and Crossref. Four highlights below — all nine papers are listed on the work page.
All nine publications (incl. 2017, 2015, 2024) → · ORCID · Google Scholar
Teaching is treated as research: build the simplest system that makes a hard idea clear, then let students break it and rebuild it.
Incident Response and Vulnerability Assessment & Penetration Testing (VAPT) — applied cybersecurity practice with system-level analysis and research-informed instruction.
Doctoral research in FPGA-based AI acceleration. Mentored students and guided laboratory work; 6 postgraduate theses supervised across AI and hardware-accelerated architectures.
Laboratory instruction in Basic Electronics — circuit fundamentals, measurement techniques and applied engineering.
Writing to make complex topics learnable — for students, for the open-source community and for myself.
I design architectures that scale intellectually as well as technically — systems that teach, explain and endure.
Engineer with an Electrical & Electronics background; PhD research (thesis submitted) at NIT Goa on VLSI and reconfigurable computing for GAN acceleration on FPGA-based edge devices. I teach cybersecurity at NFSU, build open-source tools, and write about AI, hardware and knowledge systems.
Research collaboration, hardware-accelerated ML, security education and mentorship.