Skip to content
View Arifuzzamanjoy's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report Arifuzzamanjoy

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Arifuzzamanjoy/README.md
Arifuzzaman Joy

Email LinkedIn Portfolio Google Scholar ORCID Hugging Face Profile Views


🛠️ What I Build

I build the infrastructure layer that makes LLM and AI-agent systems run in production — reliably, on serverless/decentralized GPUs, at a fraction of managed-API cost. Published ML researcher (7 peer-reviewed papers, 4 in Q1 journals, IF up to 7.1) who ships the hard part: multi-agent orchestration, RAG, and GPU deployment — not just notebooks.

  • 🚀 Production LLM / agent deployment — RunPod · Modal · Vast.ai; Dockerized serverless endpoints with CI/CD, plus self-contained installers that survive real GPU-provider failures (driver mismatches, multi-GPU OOM, topology-aware placement)
  • 🧠 Multi-agent systems with latent-space collaboration — agents exchange hidden states instead of generated text → fewer tokens, faster inference (open-sourced as LatentMAS-SLoRA)
  • 📚 RAG / document intelligence — embedding retrieval, citation tracking, multi-hop reasoning, and LLM-as-judge evaluation
  • 🎛️ Dynamic LoRA serving — hot-swappable, domain-routed PEFT adapters on a single base model, with custom LoRA training built in
  • 💸 Inference cost optimization — meaningful GPU savings and ~$0 idle cost via serverless autoscaling

📨 Tell me your model and your latency / cost target — I reply within 2 hours.


⚡ Highlight — Production Open-Source GPU Infrastructure

Light-Heart-Labs / DreamServer — a production, self-hostable AI-deployment platform for decentralized/serverless GPUs.

My contributions are merged in upstream (16 PRs, 13 merged) and span the hard infrastructure surface:

  • 🧰 p2p-GPU installer toolkit for Vast.ai — multi-phase, hardened Bash (set -euo pipefail, hard-fail ACLs), GPU-tier detection, and ~28 documented host-environment failure modes
  • 🩺 TCP/CLI health-probe routing — added health_type: http|tcp|none across schema, catalog generator, dashboard API & shell scripts, fixing silently-dropped non-HTTP services
  • 🔐 Schema & security hardeninggpu_backends validation, Docker Compose env-var hardening, shell-injection fixes across the extensions library

Stack: Bash installer hardening · Docker Compose · GPU tier detection · FastAPI · pytest · ShellCheck · Vast.ai quirks


🏆 Featured Project — LatentMAS-SLoRA

Officially featured as a community extension in Gen-Verse / LatentMAS — the repo for the LatentMAS paper (arXiv:2511.20639, 🤗 #1 Paper of the Day).

A multi-agent reasoning framework that augments LatentMAS with role-specialized, dynamically switchable LoRA adapters and latent-space collaboration — agents communicate through hidden states, not generated text. Includes VLM support (Qwen2.5-VL-7B), RAG integration, real evals, and RunPod serverless deployment with CI/CD.

Measured results: +12% accuracy · 2.7× faster inference · 63.6% token reduction vs. traditional RAG.

GitHub Demo Featured

Python · PyTorch · PEFT / LoRA · Qwen2.5-VL · RAG · RunPod · Docker · CI/CD

 Planner → Critic   (latent)
        → Refiner  (latent)
        → Judger   (text)

 + Dynamic LoRA routing
 + Domain auto-detection
 + 4 specialized adapters
 + Latent-space messaging

🧰 Tech Stack

LLM / Agent Infra

ML / DL

MLOps / Infra

Languages & Data


📌 Selected Projects

Multi-agent reasoning with dynamic LoRA routing + latent-space collaboration. Featured in Gen-Verse/LatentMAS. PyTorch PEFT Qwen2.5-VL RAG RunPod

Retrieval pipeline over URL/JSON/CSV docs with citation tracking and automated LLM-as-judge evaluation. Python RAG Embeddings Evals

Serverless RunPod worker for FLUX.2 Klein text-to-image / image-to-image — $0 idle, autoscaled. RunPod Serverless Docker Flux

End-to-end serverless inference ecosystem for diffusion models with Dockerized endpoints + CI/CD. Serverless Docker CI/CD Diffusers

Topology-aware multi-GPU pipeline with per-GPU VRAM capping (multi-GPU OOM fix) and self-host UI. torch.distributed FSDP Docker Gradio

Self-hosted Flux LoRA platform tuned for A40 (48 GB) → H200, with 4-bit quantization & batch inference. Flux LoRA CUDA Gradio

Serverless speech-to-text worker — scalable transcription endpoint on demand. Whisper RunPod Serverless

Low-cost, CPU-friendly self-hosting kit for local AI tooling with secure external sharing. Docker n8n Self-Hosting

More projects — LoRA training, NLP fine-tuning & low-VRAM inference
Project What it does Tech
Lora_Trainer_Imgen_Flux Custom LoRA training pipeline for Flux image models PEFT Flux
bangladeshi-tts-finetuning Fine-tuning TTS for Bangla speech TTS Fine-tuning
bangla-punctuation-restoration Transformer-based punctuation restoration for Bangla NLP Transformers
time-series forecasting (SOTA) State-of-the-art time-series forecasting models PyTorch Forecasting
Wan2GP Low-VRAM video generation for consumer GPUs PyTorch Gradio
Ltx-Image-to-Video Image-to-video generation with a Gradio interface LTX Gradio

🔬 Research & Publications

7 peer-reviewed papers · 4 in Q1 SCI journals (IF up to 7.1) · Google Scholar · ORCID · ResearchGate

# Paper Venue IF · Quartile Year Link
1 Machine-learning-assisted revelation of the best-performing single heterojunction thermophotovoltaic cell Sustainable Energy Technologies & Assessments 7.1 · Q1 2025 DOI · arXiv
2 Machine-learning-enabled performance exploration of AuCuSe₄ in a thermophotovoltaic cell Solar Energy 6.0 · Q1 2024 DOI
3 Numerical studies on a ternary AgInTe₂ chalcopyrite thin-film solar cell (first author) Heliyon 4.0 · Q1 2023 DOI
4 Numerical prediction of the photovoltaic performance of a CZTS-based thin-film solar cell Nano Select Q1 2023 DOI
5 Unleashing the power of open-source transformers in medical imaging (brain MRI, ~99.6% acc.) IJACSA 2024 DOI
6 Spectrum estimation for voiced speech using average weighted linear prediction Speech processing 2024 Profile
7 Enhancement of bone-conducted speech using deep transfer learning Speech processing 2024 Profile

Research themes: applied ML for materials/PV optimization, medical-imaging transformers, and speech enhancement.


📊 GitHub Analytics

GitHub Stats Top Languages
GitHub Streak

🎓 Education & Certifications

  • 🎓 B.Sc. Electrical & Electronic Engineering — University of Rajshahi, Bangladesh
  • 🏅 Deep Learning with TensorFlow (IBM) · Prompt Engineering (Vanderbilt) · SQL Advanced (HackerRank)

💬 Let's build your inference layer

"The best way to predict the future is to create it." — Alan Kay

Pinned Loading

  1. Wan2.2_multigpu_runpod_gpu_with_gradio_interface_for_selfhosting_UI Wan2.2_multigpu_runpod_gpu_with_gradio_interface_for_selfhosting_UI Public

    Python 2 2