Skip to content
View touseefurrehmanofficial's full-sized avatar
2 followers · 0 following

Block or report touseefurrehmanofficial

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.

Content in all repositories owned by your account will be closed.
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
touseefurrehmanofficial/README.md

Touseef Ur Rehman

Associate AI Engineer at 9D Technologies, Rawalpindi. I build and ship generative-AI and computer-vision features into consumer Android products with 100K to 50M+ installs.

Most of what I work on day to day is closed-source: a lyrics-to-music generation pipeline (Gemini 2.5 Flash + DiffRhythm) whose end-to-end time I cut from 4-5 minutes to 30-40 seconds, multi-GPU model serving on FastAPI behind Gunicorn and Uvicorn workers in Docker, on-device document edge-detection models that went from 74% to 92% accuracy, and a document embeddings microservice built on SentenceTransformers, LangChain and PyMuPDF. What is here is the work I can show publicly.

What I work with: Python, PyTorch, TensorFlow, Hugging Face Transformers, LoRA/QLoRA fine-tuning, GGUF / ONNX / TFLite quantization, YOLO / YOLO11, OpenCV, FastAPI, Docker, RabbitMQ, Redis, Kotlin (working knowledge)

Rawalpindi, Pakistan | LinkedIn

Pinned Loading

  1. _searchQueriesAnomalyDetection _searchQueriesAnomalyDetection Public

    Anomaly detection over search-query data: statistical baselines and evaluation. Built during the AICP machine-learning internship.

    Jupyter Notebook

  2. _transactionAnomaliesDetection _transactionAnomaliesDetection Public

    Anomaly detection on financial transaction data, for fraud and outlier review. Built during the AICP machine-learning internship.

    Jupyter Notebook

  3. _userProfilingAndSegmentation _userProfilingAndSegmentation Public

    User profiling and segmentation pipelines supporting targeted marketing analysis. Built during the AICP machine-learning internship.

    Jupyter Notebook

  4. app_user_segmentation app_user_segmentation Public

    App user segmentation: clustering and cohort analysis on behavioural data.

    Jupyter Notebook

  5. infinite_sight infinite_sight Public

    Voice-controlled Flutter accessibility app for visually impaired users. Custom CNN (TensorFlow/Keras) classifying 14 categories of Pakistani banknotes, converted to TFLite for fully offline on-devi…

    Dart

  6. Instagram_Reach_Forecasting Instagram_Reach_Forecasting Public

    This repository provides a structured approach to analyzing and forecasting Instagram reach using historical data. The primary goal is to identify patterns, trends, seasonality, and anomalies to de…

    Jupyter Notebook