Software Engineering student at IUT, NLP researcher, backend engineer, and academic builder from Bangladesh — working at the intersection of language, law, and low-resource AI.
I am a final-year Software Engineering student at the Islamic University of Technology (IUT), deeply focused on Natural Language Processing, Computational Mathematics, Legal AI, and Large Language Models. My work combines research, engineering, and open-source development with the goal of building impactful systems and publishing internationally recognized research.
I actively work on research-oriented datasets, multilingual NLP systems, information-extraction pipelines, and analytical AI platforms — with a bias toward low-resource languages and culturally grounded benchmarks.
Topics I actively read, build, and write papers on.
Selected work spanning figurative language, political alignment in LLMs, evaluation geometry, and game-theoretic benchmarks for dialogue.
A culturally grounded dataset of 10,361 Bengali idioms annotated with a 19-field schema capturing semantic, syntactic, cultural, and religious dimensions. Benchmarks 30 multilingual / instruction-tuned LLMs — none exceed 50% accuracy versus 83.4% human.
arXiv:2602.12921Audits 26 contemporary LLMs using three political psychometric inventories (Political Compass, SapplyValues, 8Values) plus a large news-bias labeling task. Shows 96.3% of models cluster in the Libertarian-Left quadrant — model identity, not prompt wording, explains most variance.
arXiv:2601.06194A SoK paper merging multitrait–multimethod (MTMM) analysis with geometric representations to organize and interpret LLM evaluation results across many benchmarks. Treats models as points in a capability space and argues for moving from leaderboard fragments to structured, geometry-aware capability maps.
arXiv:2605.08522A game-theoretic benchmark with two tasks — social-deduction style AIDG-I and a structured "20 Questions" style AIDG-II. Across 439 games with six frontier models, finds a pronounced asymmetry: containment is far stronger than deduction (~350 ELO defensive advantage).
arXiv:2602.17443A multi-turn zero-sum negotiation game over financial resources to jointly evaluate persuasion and resistance in LLMs. Shows the two abilities are only weakly correlated; models defend better than they attack.
arXiv:2602.16639Also: technical articles published in Python in Plain English on Medium.
Selected open-source projects across NLP, automation, graphics, and tooling.
Turns plain-language math prompts into short Manim animations. Plans the explanation, generates scene code, repairs failed code, and stitches the final video. Supports OpenRouter, OpenAI, Gemini.
RepositoryA web platform for mathematical enthusiasts: contests, problem-solving, community engagement. Built with Laravel, Filament, Livewire — featuring a Sergent-to-General rating system and collaborative forums.
RepositoryA zero-dependency JS library that renders 2D mathematical graphics from a natural-language-like DSL into SVG in the browser — declarative geometry, plotting, intersection solving, smart labeling.
A Discord bot bridging Zotero with Discord and Google Sheets. Extracts color-coded PDF annotations and routes them to categorized channels — yellow → methods, green → contributions, blue → results, purple → claims, red → limitations.
RepositoryAI-powered scraper extracting crime news from 40 verified sources across 6 continents. Uses spaCy NER and crime classification, SHA-256 + MD5 dedup, and daily GitHub Actions runs. Outputs an 18-column structured CSV.
RepositoryA comparative study of 15 pretrained CNN architectures for character-level static hand-gesture recognition (37 classes, 1,500 images each). Includes Grad-CAM, LIME, t-SNE, and full evaluation suites.
RepositoryA .NET 6+ CLI that analyzes directory structures and generates XML reports about a codebase. Produces folders.xml, files.xml, stat.xml, and a combined complete.xml report — with intelligent exclusion of build folders.
RepositoryA Java toolkit covering algebra, trigonometry, matrices, vectors, number systems, combinatorics, coordinate geometry, and bitwise ops — with JavaDoc and a JAR release.
RepositoryPublic datasets I've built and released on Kaggle to support research in low-resource NLP, legal AI, and game simulation.
The largest computational resource for Bengali idioms — 19-field schema, 37,129 semantic tag assignments, sentiment & cultural metadata. Accompanies the LREC 2026 paper on figurative understanding.
Bangladesh's legal framework (1799–2025) — 35,633 sections, 14,523 footnotes, government & legal-system context. Multilingual: English, Bengali, mixed. CC-BY 4.0.
100,000 simulated tournaments across 16 psychologically-inspired AI agents — group stage, knockouts, and full replay sequences. ~2.3GB CSV for behavioral modeling and strategy analysis.
A perfectly balanced dataset (3,562 crime / 3,562 non-crime) for binary classification — useful for logistic regression, decision trees, and deep-learning baselines.
Two decades of BdMO papers, organized by year, level (Primary → Higher Secondary), and round (Divisional, Regional, National, Selection).
A full record of my undergraduate journey at IUT, alongside earlier academic history. Detailed semester results are tucked behind expandable panels to keep this page calm.
| Course | Credit | Grade |
|---|---|---|
| CSE 4104 Engineering Drawing Lab | 0.75 | A |
| CSE 4107 Structured Programming I | 3 | A |
| CSE 4108 Structured Programming I Lab | 1.5 | A+ |
| Hum 4142 Arabic I | 1 | A+ |
| Hum 4145 Islamiat | 2 | A+ |
| Hum 4147 Technology, Environment and Society | 3 | A |
| Math 4141 Geometry and Differential Calculus | 4 | A+ |
| Phy 4143 Physics II | 3 | A− |
| Phy 4144 Physics II Lab | 0.75 | A+ |
| SWE 4101 Introduction to Software Engineering | 3 | A+ |
| Course | Credit | Grade |
|---|---|---|
| CSE 4203 Discrete Mathematics | 3 | A+ |
| CSE 4205 Digital Logic Design | 3 | A+ |
| CSE 4206 Digital Logic Design Lab | 0.75 | A+ |
| Hum 4242 Arabic II | 1 | A+ |
| Hum 4247 Accounting | 3 | A+ |
| Hum 4249 Business Psychology and Communications | 3 | A− |
| Math 4241 Integral Calculus and Differential Equations | 4 | A+ |
| SWE 4201 Object Oriented Concepts I | 3 | A+ |
| SWE 4202 Object Oriented Concepts I Lab | 1.5 | A+ |
| Course | Credit | Grade |
|---|---|---|
| CSE 4303 Data Structures | 3 | A+ |
| CSE 4304 Data Structures Lab | 1.5 | A+ |
| CSE 4305 Computer Organization and Architecture | 3 | A+ |
| CSE 4307 Database Management Systems | 3 | A |
| CSE 4308 Database Management Systems Lab | 1 | A+ |
| CSE 4309 Theory of Computing | 3 | A+ |
| Math 4341 Linear Algebra | 3 | A+ |
| SWE 4301 Object Oriented Concepts II | 3 | A+ |
| CSE 4302 Object Oriented Concepts II Lab | 1.5 | A+ |
| SWE 4304 Software Project Lab I | 1.5 | A+ |
| Course | Credit | Grade |
|---|---|---|
| CSE 4403 Algorithms | 3 | A+ |
| CSE 4404 Algorithms Lab | 1 | A+ |
| CSE 4409 Database Management Systems II | 2 | A |
| CSE 4410 Database Management Systems II Lab | 1.5 | A+ |
| CSE 4411 Data Communication and Networking | 3 | A+ |
| CSE 4412 Data Communication and Networking Lab | 1 | A+ |
| Hum 4441 Engineering Ethics | 3 | B+ |
| Math 4441 Probability and Statistics | 3 | A+ |
| SWE 4401 Software Requirements and Specifications | 3 | A+ |
| CSE 4402 Software Requirements and Specifications Lab | 1 | A+ |
| SWE 4404 Software Project Lab II | 1.5 | A+ |
| Course | Credit | Grade |
|---|---|---|
| CSE 4501 Operating Systems | 3 | A |
| CSE 4502 Operating Systems Lab | 1 | A+ |
| CSE 4553 Machine Learning | 3 | A |
| CSE 4554 Machine Learning Lab | 0.75 | A+ |
| Math 4543 Numerical Methods | 3 | A |
| Math 4544 Numerical Methods Lab | 0.75 | A+ |
| SWE 4501 Design Patterns | 2 | A+ |
| SWE 4502 Design Patterns Lab | 1 | A+ |
| SWE 4503 Software Security | 3 | A+ |
| SWE 4504 Software Security Lab | 0.75 | A+ |
| SWE 4506 Design Project I | 1.5 | A+ |
| SWE 4537 Server Programming | 3 | A+ |
| SWE 4538 Server Programming Lab | 0.75 | A+ |
| Course | Credit | Grade |
|---|---|---|
| CSE 4617 Artificial Intelligence | 3 | A− |
| CSE 4618 Artificial Intelligence Lab | 0.75 | A+ |
| CSE 4621 S Microprocessor and Interfacing | 3 | A |
| CSE 4622 S Microprocessor and Interfacing Lab | 0.75 | A+ |
| Math 4643 Probability and Statistics II | 3 | A+ |
| SWE 4601 Software Design and Architectures | 3 | A |
| SWE 4602 Software Design and Architectures Lab | 0.75 | A |
| SWE 4603 Software Testing and Quality Assurance | 3 | A |
| SWE 4604 Software Testing and Quality Assurance Lab | 1 | A+ |
| SWE 4606 Design Project II | 1.5 | A+ |
| SWE 4637 Web and Mobile Application Development | 3 | A+ |
| SWE 4638 Web and Mobile Application Development Lab | 0.75 | A+ |
| Course | Credit | Grade |
|---|---|---|
| CSE 4714 Technical Report Writing | 0.75 | A+ |
| HUM 4747 Legal Issues and Cyber Law | 3 | A+ |
| SWE 4700 Project / Thesis | 1.5 | A+ |
| SWE 4701 Software Metrics and Process | 3 | A+ |
| SWE 4739 Embedded Software Development | 3 | A− |
| SWE 4740 Embedded Software Development Lab | 0.75 | A+ |
| SWE 4790 Internship | 9 | A+ |
Stars, cosmology, observational astronomy — and the societies that gather around them.
Sci-fi and science-themed media — narrative as a way to think about systems.
Civilizations, manuscripts, and the long arc of cultural memory in the subcontinent.
Long-form academic conversations — the kind that shape future papers.
To build impactful AI systems, contribute meaningful research to the NLP community, and develop technologies that help low-resource languages and human ecosystems gain stronger representation in modern AI.
Open to research collaboration, internships, and conversations on NLP, legal AI, and low-resource language technology.
sakhadib@gmail.com