Skip to content
View theraihanrakibb's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report theraihanrakibb

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
theraihanrakibb/README.md

Typing SVG

     


I'm an AI Infrastructure Engineer who builds fast, cost-efficient LLM serving systems. I take inference research — KV-cache disaggregation, FP4 quantization, and RDMA-scale compute — and turn it into measurable production wins on A800/H200 clusters. I'm an M.Eng. candidate at NWPU and the author of NVFP4-DiT (IEEE TMM, under review).

Currently

  • 🛠️ Building a 10-project open-source AI-infra portfolio to sharpen and showcase production engineering.
  • 📄 Writing my M.Eng. thesis on multimodal deepfake detection.
  • 💡 Open to AI Infrastructure / LLM-serving engineering roles.

My Journey

flowchart LR
    BD[Bangladesh] --> CN[China: Xi'an]
    CN --> BS[NWPU: BSc in CST]
    BS --> MS[NWPU: MEng in SWE]
    MS --> AI[AI Infrastructure Engineer]
    MS --> RS[NVFP4-DiT Research]
    AI --> PF[10-Project Open-Source Portfolio]
    RS --> PF
    PF --> FUT[The Road Ahead]
Loading

What I Do

  • AI Infrastructure — KV-cache architecture, prefill/decode disaggregation, SGLang/vLLM, RDMA, A800/H200 clusters.
  • Low-Precision Inference — FP8/FP4 quantization for LLMs and diffusion transformers.
  • M.Eng. Software Engineering @ NWPU — LLM inference optimization & multimodal AI.

Focus

  • LLM Serving at Scale — KV-cache disaggregation (PD split), prefix caching & continuous batching on SGLang/vLLM across A800/H200.
  • Low-Precision Inference — FP8/FP4 quantization for LLMs and diffusion transformers; author of NVFP4-DiT (IEEE TMM, under review).
  • Distributed GPU Systems — RDMA-based multi-node training/inference and cluster orchestration.
  • GPU Kernels — CUDA / Triton / FlashAttention kernels for attention and GEMM.
  • Multimodal AI — audio-visual-temporal fusion for deepfake detection and video generation.

Key Achievements

Metric Result Context
KV-cache hit rate 92.27% prefix-cache tuned serving
TTFT reduction 8.3× 4× A800 PD-disaggregation
Memory reduction FP4 quantization (NVFP4-DiT)
Thesis 70 pages multimodal deepfake detection
Scholarship Chinese Gov. Scholarship NWPU M.Eng.

Experience

AI Infrastructure Engineer Intern · InfiX.ai · Shenzhen, China · Apr 2026 – Jun 2026

Education

Degree University Period
M.Eng. Software Engineering Northwestern Polytechnical University (985/211) Sep 2024 – Mar 2027
B.Eng. Computer Science & Technology Northwestern Polytechnical University (985/211) Sep 2020 – Jul 2024

Research Interests

  • AI Infrastructure & LLM Inference Systems (KV-cache, PD disaggregation, RDMA)
  • Multimodal AI (visual + audio + temporal fusion, deepfake detection, video generation)
  • Low-Precision Quantization (FP8/FP4 for diffusion transformers and LLMs)
  • GPU Kernel Optimization (CUDA, Triton, FlashAttention, GEMM)

Open to Collaboration

  • LLM serving infrastructure and distributed systems
  • Multimodal AI and computer vision research
  • Open-source AI tooling and frameworks
  • Always happy to connect via email or LinkedIn

🚀 AI Infrastructure Portfolio

A curated set of 10 production-quality, fully-tested, Dockerized AI-infra projects — each with a clear architecture, quickstart, and CI. Showcased in ai-infra-portfolio.

Project Area What it does
llm-gateway LLM Gateway OpenAI-compatible proxy: per-key rate limits, cost caps, caching, provider fallback.
mini-serve Model Serving Inference server: dynamic batching, SSE streaming, Prometheus metrics.
gpu-exporter Observability NVIDIA GPU Prometheus exporter + Grafana dashboard.
train-launcher Training Ops Fault-tolerant multi-node PyTorch launcher with auto-retry.
model-registry MLOps Content-addressed model/dataset registry (mini-MLflow) with aliases.
kv-cache-sim Inference Eff. KV-cache eviction + prefill/decode disaggregation simulator (TTFT/TPOT).
llm-bench Benchmarking LLM benchmark/eval harness: TTFT, TPOT, throughput, cost model.
quant-playground Low Precision FP8/FP4/INT8/INT4 bit-packing + numpy MLP quantization demo.
llmoops-trace Observability OpenTelemetry LLM tracing collector + Grafana dashboard.
rag-pipeline Retrieval (RAG) Offline RAG toolkit: ingest → chunk → embed → ANN search → rerank.

Featured Research & Engineering

Project Description
NVFP4-DiT 4-bit low-precision audio-guided video diffusion transformer (IEEE TMM, under review).
DeepfakeAudioVisualTemporalDetector Multimodal deepfake detection: EfficientNet + FFT + MFCC + Transformer + Attention Fusion.
c-compiler-frontend 4-stage C compiler front-end: lexical, syntax, semantic analysis + three-address code generation (Flex/Bison).
Online-Portfolio Personal portfolio website.

Publication

  • NVFP4-DiT: 4-bit Audio-Guided Video Diffusion Transformers — IEEE TMM, under review.

Tech Stack

Python C++ CUDA PyTorch SGLang vLLM Triton FastAPI Docker Kubernetes Linux


GitHub Stats

GitHub Profile Details
Repos per Language Most Commit Language
Realtime Contribution Graph

“Inference is where the model meets the metal — I make that intersection fast, cheap, and observable.”

Pinned Loading

  1. ai-infra-portfolio ai-infra-portfolio Public

    Curated portfolio of 5 small, production-quality AI-infrastructure projects (serving, observability, training, MLOps, gateway).

    1

  2. DeepfakeAudioVisualTemporalDetector DeepfakeAudioVisualTemporalDetector Public

    Multimodal Deepfake Detection Framework | Visual (EfficientNet+FFT) + Audio (MFCC) + Temporal (Transformer) | Attention Fusion | WildDeepfake | PyTorch

    Python 1

  3. NVFP4-DiT NVFP4-DiT Public

    NVFP4-DiT: Theory and Practice of 4-Bit Low-Precision Training and Inference for Audio-Guided Video Diffusion Transformers

    TeX 1

  4. Online-Portfolio Online-Portfolio Public

    Personal portfolio website showcasing projects, skills, and experience

    HTML

  5. c-compiler-frontend c-compiler-frontend Public

    C compiler implementation with lexer, parser, and code generation using Yacc/Lex

    Yacc

  6. sgl-project/sglang sgl-project/sglang Public

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Python 30.5k 7.3k