Work beyond boundaries

Building Intelligent
Data Systems

Data Engineer specializing in scalable ETL pipelines, machine learning, and distributed computing. Published researcher with expertise in deep reinforcement learning and generative AI.

View Projects View Resume
Muhammad Sarmad Sohail

Muhammad Sarmad Sohail

Data Engineer | ML Engineer

1+
Year Exp
1
Publication
10+
Projects
Who I Am

About Me

Passionate about leveraging data and AI to solve complex problems at scale

I'm a Data Engineer at Adept Tech Solutions, where I build scalable ETL pipelines and synthetic data platforms using PySpark and FastAPI. My work focuses on distributed computing, data profiling, and production-grade microservices.

With a background in Electrical Engineering from NUST, I've published research at IEEE WCNC 2024 on deep reinforcement learning for IoT networks. I combine strong engineering fundamentals with cutting-edge ML techniques.

Recently earned Top Performer recognition at the Pak Angels GenAI Hackathon, building AI-powered systems using BERT, LLaMA, and LangChain. I'm passionate about generative AI, RAG systems, and autonomous agents.

Data Engineering

PySpark FastAPI SQL ETL Pipelines Kafka

Machine Learning

TensorFlow PyTorch Deep RL Transformers LangChain

Tools & Languages

Python Git Docker Linux MATLAB
Portfolio

Featured Projects

Building scalable systems and pushing the boundaries of AI

Research Published

Resource Allocation in MEC-NOMA Networks

Deep Reinforcement Learning framework optimizing computation offloading for energy-harvesting IoT devices. Achieved superior performance over baseline methods with faster convergence and minimized service delay.

Python TensorFlow Deep RL DDPG
📄 Paper 🎥 Demo 💻 Code 📊 Poster
🏆 Top Performer

ZeroPhish Gate

Hybrid AI-powered phishing detection combining BERT and LLaMA for supply chain security. Winner of Top Performer award at Pak Angels GenAI Hackathon among competitive cohort.

BERT LLaMA LangChain Gradio
💻 Code 🏆 Certificate
Computer Vision

CNN-LSTM Action Recognition

Novel Conv2D + LSTM architectures for video-based regression on UBFC dataset. Implemented custom preprocessing pipelines and data augmentation strategies.

PyTorch Keras CNN LSTM
💻 Code
Production

ASCEND Synthetic Data Platform

Production-grade distributed ETL pipelines for data profiling, feature engineering, and synthetic data generation. Built scalable microservices with FastAPI and PySpark to orchestrate high-volume data workflows. The platform supports end-to-end synthetic data creation pipelines used for advanced analytics, model training, and privacy-preserving data sharing across teams.

PySpark FastAPI ETL Microservices
🔒 Proprietary
GenAI

RAG System with Groq & FAISS

Retrieval-Augmented Generation system using Groq LLM and FAISS vector database for efficient document querying and context-aware responses.

LangChain Groq FAISS Gradio
💻 Code
Computer Vision

AI Construction Damage Analyzer

Vision-based chatbot for analyzing construction damage images using multimodal AI. Deployed as interactive Gradio application for real-time assessment.

Vision Models LLM Gradio
💻 Code
IC Design

Passive RFID Transponder Chip

Ultra-low power RFID chip for animal tagging using CMOS 65nm technology. Focused on power optimization, reliability, and market competitiveness.

Cadence Virtuoso CMOS 65nm RFID
🔒 NCDC
NLP

Real-Time Meeting Summarizer

AI-powered transcription and summarization tool for meetings. Uses speech-to-text and LLM-based summarization for actionable insights.

Whisper LangChain Streamlit
💻 Code
AI Agents

Autonomous AI Agent Demo

Multi-agent system demonstrating autonomous decision-making and task execution. Implements ReAct framework for reasoning and action.

LangChain Agents Python
💻 Code
Digital Design

4-bit Microprocessor & VGA Controller

Custom 4-bit microprocessor with hierarchical datapath and control logic. Implemented VGA line-drawing algorithms in Verilog for FPGA deployment.

Verilog FPGA Digital Logic
🎓 Academic
Research

Publications

Contributing to the advancement of AI and IoT systems

📄

Optimizing Resource Allocation in MEC-Enabled CR-NOMA-Assisted IoT Networks: A DRL-Driven Strategy

IEEE WCNC 2024 Dubai, UAE May 2024

Muhammad Taha Qaiser, Muhammad Sarmad Sohail, Minahil Shafqat, Syed Asad Ullah, Haejoon Jung, Syed Ali Hassan

Proposed a Deep Deterministic Policy Gradient (DDPG) framework for optimizing resource allocation in energy-harvesting IoT devices using CR-NOMA and Mobile Edge Computing. Demonstrated superior performance over baseline methods with faster convergence.

📄 Read Paper 🎥 Watch Demo 📊 View Poster
Get In Touch

Let's Work Together

Open to collaborating on data engineering and ML projects

✉︎