The curriculum vitae, in proof

Masthead

Summary

1. Title

   MSc, Computer Science and Engineering — BRAC University, Dhaka

   Date

   Fall 2026 —

   Detail

   Thesis proposal accepted: HCGT-PG. Supervisor: Dr. Badhan Das.
2. Title

   BSc, Computer Science and Engineering — BRAC University, Dhaka

   Date

   Fall 2021 – Summer 2026

   Detail

   CGPA 3.31 / 4.00. Thesis: HierarchiRetina, supervised by Rafeed Rahman, deposited in the BRAC University institutional repository. Coursework in machine learning, deep learning, compilers, theory of computation, DBMS, operating systems, algorithms and software engineering.
3. Title

   Higher Secondary Certificate — Uttara High School and College, Dhaka

   Date

   2020

   Detail

   GPA 5.00 / 5.00. Science.
4. Title

   Secondary School Certificate — Ullapara Merchant Pilot High School, Sirajganj

   Date

   2018

   Detail

   GPA 4.72 / 5.00. Science.

1. Title

   HierarchiRetina

   Date

   2026

   What it does

   Interpretable diabetic retinopathy grading from retinal photographs

   Detail

   Supervisors: Rafeed Rahman, Niloy Farhan, Md. Golam Rabiul Alam. Deposited.
2. Title

   Rank Radii Transfer as Quantiles

   Date

   2026

   What it does

   Placing unseen species inside the taxonomy, not in flat clusters

   Detail

   Supervisor: Niloy Farhan. Under review.
3. Title

   Automated Renal Reporting

   Date

   2026

   What it does

   The aim: a generator that cannot emit a value it did not measure

   Detail

   Supervisor: Niloy Farhan. In preparation.
4. Title

   HCGT-PG

   Date

   2026

   What it does

   What would happen if you knocked the gene down

   Detail

   Supervisor: Dr. Badhan Das. Proposal accepted.

1. Title

   HierarchiRetina: A Multi-Stage Deep Learning Pipeline for Diabetic Retinopathy Severity Assessment

   Date

   Published 2026

   Detail

   BSc thesis, BRAC University
2. Title

   Rank Radii Transfer as Quantiles: Taxonomic Placement and Sub-Taxonomy Construction for Unseen Species

   Date

   Under review 2026
3. Title

   Automated Renal Reporting

   Date

   In preparation 2026

1. Title

   ResearchLens — evidence-grounded literature retrieval

   Detail

   Evidence-grounded RAG over 106 papers, 15,664 passages, plus a live-fetched index of my own site and textbook (Python, FastAPI, ONNX, Gradio). Structure-preserving PDF parsing; hybrid BM25 + dense retrieval with RRF fusion and cross-encoder reranking; mechanically enforced grounding — computed citations, fabricated-marker removal, refusal when unsupported. Per-session document upload isolated from the shared index; subset-scoped retrieval; related-work discovery across arXiv, PubMed and OpenAlex; benchmark harness with hand-labelled ground truth. 293 tests, deployed on Hugging Face, runs locally with no API key.
2. Title

   LocalScholar — a private, laptop-scale research assistant

   Detail

   Local-first RAG research assistant (FastAPI, React, ONNX, Ollama). Hybrid BM25 + dense retrieval with RRF fusion and cross-encoder reranking; measured ablation to Recall@5 0.933, MRR 0.840; verified refusal on unanswerable questions; citations computed from passage overlap rather than self-reported. 100 tests, runs offline on 8 GB.
3. Title

   PRISMA-Local — screening a systematic review on your own hardware

   Detail

   Local LLM screening assistant for systematic reviews (PyTorch, PEFT, vLLM, Gradio). QLoRA 4-bit fine-tune of Qwen2.5-7B and LoRA fine-tunes of Qwen2.5-3B scoring title+abstract against a protocol in one token, ranked by logit margin; trained on 67 SYNERGY reviews, evaluated on 6 held out at natural prevalence (13,665 records, 4.6% positive). Cross-topic transfer with zero in-review labels: WSS@95% 0.331 vs 0.129 zero-shot, reported level with a TF-IDF baseline and below active learning, both computed rather than cited. Diagnosed a bf16 softmax collapsing 13,665 records onto 45 distinct scores — recall@10% +26% after an fp32 fix that moved AUC by 0.002 — and made score resolution a logged, failing condition. vLLM prefix caching 1.40x. In-browser demo, RIS in and RIS out.

1. Title

   Vi-Graph — diagram images turned into editable, queryable graphs

   Detail

   Diagram-to-graph reconstruction with a fine-tuned vision-language model (PyTorch, Transformers, PEFT/QLoRA, FastAPI, Next.js, React Flow). Qwen3-VL-2B with 4-bit QLoRA: 17.4M trainable parameters, 1.4 hours, 7.6 GB peak memory. Built a 2,800-diagram synthetic benchmark with unseen test layouts and 25,698 structural questions. On 500 held-out diagrams: graph similarity 0.581 → 0.740, edge F1 from 0.499 to 0.638, structural QA 0.437 → 0.582, valid graphs 72% → 91%, all p < 0.001 (paired bootstrap, Holm). Reported an OCR + OpenCV baseline that ties on graph similarity (0.738); diagnosed runaway enumeration on dense diagrams and added a guard that cut evaluation time 26% with no significant score change. Schema-validated output with logged repair, graph-grounded QA, exports; 767 tests.
2. Title

   Winnow — a free, self-hostable platform for systematic reviews

   Detail

   Free, open-source, self-hostable platform for systematic, scoping and rapid reviews (FastAPI, PostgreSQL, Redis, React, TypeScript, Docker, Caddy). Import from six citation formats, automatic deduplication, dual blind screening with conflict resolution, relevance ranking that retrains per reviewer with a stopping estimate, open-access full-text retrieval with virus scanning, dual data extraction with consensus, four risk-of-bias instruments, and PRISMA 2020 output with Cohen's and Fleiss' kappa. Authorisation checked per review with PostgreSQL row-level security behind it and blind mode enforced server-side; Argon2id, 2FA, OIDC sign-in, append-only audit log, OWASP ZAP baseline clean in CI. Measured against written budgets on 100,000-record reviews: screening p95 32–69 ms, import 49 s, deduplication of 50,000 in 13 s, LCP 0.7 s on 4G; 50 concurrent reviewers at p95 37 ms with 0 errors in 19,920 requests. WCAG 2.2 AA with no serious axe findings across 43 pages; 900 backend tests at 95% coverage, Playwright e2e, mypy --strict. Specified as a ten-phase plan with per-phase acceptance criteria and built with AI coding agents against those gates; ~150 commits.
3. Title

   SANDHI Research Lab — a public website, member workspace and administration in one application

   Detail

   Research lab platform, live at sandhiresearch.org (Next.js 16, React 19, TypeScript, PostgreSQL/Prisma, Better Auth, Cloudflare R2, Resend, Vercel). Public site with a research map, project progress, publications and Bengali-aware full-text search; member workspace with task boards, meeting notes, an append-only experiment log and Markdown drafting with review; sixteen administrative managers with an audit log. Invitation-only accounts, mandatory 2FA with passkeys, breach-checked passwords, audit written in the same transaction as each change, signed links for private files. Data-layer caching invalidated by every edit under a nonce-based CSP; search on PostgreSQL full-text indexes. 101 pages, 48 data models, 400+ unit and 140+ Playwright tests including security boundaries and accessibility; first commit to production in 14 days.
4. Title

   Lucy — an AI desktop companion that runs entirely on the Mac

   Detail

   macOS AI desktop companion (Tauri 2, Rust, TypeScript, three.js/VRM, Apple Speech, Ollama, Kokoro TTS on ONNX). Code-driven 3D character with spring-bone physics and six moods; hands-free wake word on Apple's on-device recogniser; local neural voice whose expression tags drive face and pacing. Rust owns all native access and every network call, keys in the Keychain, and the webview's CSP permits no network; any OpenAI-compatible provider or Anthropic, local and free by default. Click-through transparent overlay via a hit-test thread, cursor petting from a Rust watcher, a deterministic calculator in place of model arithmetic, gapless speech by synthesising ahead. 12–30 fps idle, ~190 MB voice server faster than real time. 146 Vitest and 48 Rust tests, clippy -D warnings, CI on Linux and macOS.
5. Title

   Officina AI — an execution tracer for Python, C and Java, with a tutor that explains the trace

   Detail

   Execution tracer for Python, C and Java that runs in the browser (Pyodide, tree-sitter, clang in WebAssembly, the Eclipse compiler on CheerpJ, Cloudflare Workers AI). Python traced under sys.settrace with AST-instrumented conditions; C and Java instrumented at the source with insert-only edits that keep every line number, compiled in the browser and traced by their own runtimes — C variables read back by address, pointers named by their targets, out-of-bounds, divide-by-zero and NULL caught on the line. One step format for all three, checkpointed so any of 50,000 steps shows in under 1 ms. LLM tutor grounded in the recorded facts, behind a same-origin, rate-limited Worker. Every C and Java example traced natively in CI against its untraced output.
6. Title

   Officina — a notebook that compiles and runs Python, C, C++ and Java in the browser

   Detail

   Browser-only notebook for Python, C, C++ and Java (Pyodide, clang and wasm-ld compiled to WebAssembly, the Eclipse compiler on CheerpJ). Python runs in a Web Worker with the network APIs removed, with Stop, a 30 s limit and a 256 KB output cap; C and C++ are genuinely compiled and run in the browser; notebooks persist locally and export as .ipynb. No server; the example library is edited from the site's CMS.
7. Title

   MONAI — the metric that hid the failures

   Detail

   Open-source contribution to MONAI (Project-MONAI/MONAI, 8.7k stars), the standard medical imaging framework. Found a silent correctness bug in HausdorffDistanceMetric: a prediction that misses the structure entirely returns nan at every percentile where the maximum returns inf, and nan is excluded from the reduction, so failed cases are dropped from a dataset HD95 rather than scored. Demonstrated that the reported metric does not move as a model degrades from 0 to 99 misses in 100 images. Traced to torch.quantile interpolating between two infinities; fixed with a guard and twelve regression tests, verified failing before and passing after. Reported as issue #9095; the fix is PR #9096, under review.
8. Title

   CSMMS — Campus Student Management and Marketplace System

   Detail

   FastAPI backend: REST API design, filtered and paginated marketplace, S3 and CloudFront image upload, service impact metrics, SQLAlchemy, JWT, Alembic.
9. Title

   Leveraging CNN and Random Forest for Accurate Food Expiry Prediction

   Detail

   AI-driven food expiry prediction model combining CNNs for image analysis with Random Forest and MLP algorithms to evaluate environmental metadata (temperature, humidity, storage duration) and minimize food waste.
10. Title

    Compiler symbol table

    Detail

    Scoped symbol table for a compiler front end using lex and yacc/bison, with cross-platform builds on Linux and macOS.

1. Title

   Languages

   Detail

   Python (primary). C (coursework level).
2. Title

   Deep learning

   Detail

   PyTorch, timm, segmentation_models_pytorch. Mixed-precision training with GradScaler tuning, EMA, test-time augmentation, k-fold CV with resumable per-fold checkpointing, class-imbalance handling (pos_weight, weighted samplers), threshold calibration on validation only, ordinal regression (CORN), mixture-of-experts, cross-attention fusion, attention gates, ASPP, GeM pooling, deep supervision, frozen-backbone transfer, Grad-CAM.
3. Title

   Architectures used hands-on

   Detail

   ConvNeXt V2, Swin UNETR V2, DINOv2/v3, EfficientNet, U-Net, U-Net++, Attention U-Net, SwinHRUNetPP, HSMoE-AUNet, image-text encoders.
4. Title

   Medical imaging

   Detail

   Fundus photography, non-contrast CT, NIfTI and DICOM handling, FOV masking with morphological erosion, CLAHE on the green channel, retinal cropping, patch extraction and stitching, lesion-level connected-component evaluation, de-identification, radiologist report parsing.
5. Title

   Evaluation

   Detail

   QWK, ICC, AUC-ROC, AUC-PR, Dice, IoU, NMI, lesion-level and image-level recall, sensitivity/specificity tradeoff analysis, per-dataset breakdowns, held-out test discipline and leakage assertions.
6. Title

   Causal inference and computational biology

   Detail

   Causal graphs and DAGs, d-separation, interventions, counterfactual reasoning, gene perturbation analysis, gene regulatory network inference, multi-omics integration and biomarker discovery.
7. Title

   Data

   Detail

   pandas, NumPy, Albumentations, OpenCV, Matplotlib, Seaborn, scikit-learn, nbformat.
8. Title

   Backend

   Detail

   FastAPI, REST APIs, SQLAlchemy, JWT auth, Alembic, AWS S3, CloudFront.
9. Title

   MODEL FAMILIARITY

   Detail

   Beyond the architectures I have used hands-on, I regularly study modern vision, multimodal, language, medical imaging and computational biology models. This includes SigLIP 2, EVA-CLIP, SAM 3, nnU-Net, ViT, Qwen, Llama, DeepSeek, Kimi, MedGemma and genomic models such as AlphaGenome and Geneformer. I focus on understanding their architecture, training objective, scaling behavior, benchmarks, limitations and practical use rather than treating familiarity with a model as equivalent to hands-on experience. The model notes I keep are part of this ongoing study.
10. Title

    READING

    Detail

    I love reading books and research papers. My current reading is centered on machine learning, causality and computational biology. Key books include The Book of Why, Causality: Models, Reasoning, and Inference, Causal Inference in Statistics: A Primer, and Elements of Causal Inference: Foundations and Learning Algorithms. The reading is not separate from the research work. It is mainly about understanding what can be inferred from data, where the assumptions enter, and how interventions can provide stronger evidence than observation alone.
11. Title

    Other

    Detail

    Git, Jupyter, LaTeX, lex/yacc, CUDA-level debugging.

1. Title

   Languages

   Detail

   Bangla, native. English, full professional proficiency and the medium of instruction throughout undergraduate study.
2. Title

   Reading and research interests

   Detail

   Machine learning, computer vision, multimodal AI, language models, computational biology, representation learning, causal inference, and philosophy of science. Regularly read and write about research literature across these areas, while also reviewing research papers, books, AI models, and ideas in philosophy, science, causality, and the foundations of knowledge.