Skip to content
View mafaq229's full-sized avatar
0 followers · 3 following

Achievements

Achievement: YOLOAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: Pull Shark

Block or report mafaq229

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
mafaq229/README.md

Muhammad Afaq

ML Engineer — Production ML Systems (Cloud + Edge) • Computer Vision • Agentic AI
MSc CS (ML Specialization) @ Georgia Tech (OMSCS) | Dubai, UAE

Profile

I build end-to-end ML systems that move from experimentation to reliable production—covering data/experiment management, model development, deployment, and operational feedback loops. My work spans traditional machine learning, computer vision and agentic AI use cases, with an engineering-first approach to reliability, evaluation, and scalability.

Core Focus Areas

Agentic AI

  • Designing tool-using agents that connect to real systems (APIs, knowledge bases, internal tools)
  • Retrieval-augmented generation (RAG) patterns, grounding, and guardrails
  • Evaluation discipline: quality metrics, failure-mode analysis, latency/cost trade-offs

Machine Learning Systems

  • Reproducible pipelines, experiment tracking, and model lifecycle management
  • Deployment-ready packaging (containerization), versioning, and release practices
  • Monitoring-oriented thinking: instrumentation, drift/quality signals, iterative improvement

Computer Vision

  • Building CV workflows end-to-end: data-centric iteration, model selection, evaluation, and deployment
  • Practical post-processing and system integration for real-world constraints

Technical Stack

Languages: Python, SQL, No-SQL, C (currently learning) ML/DL: PyTorch, TensorFlow, scikit-learn
MLOps / Engineering: Docker, Git, Linux, MLflow, DVC
GenAI: LLM applications, agent orchestration patterns, RAG, evaluation/guardrails
Analytics: Power BI
Systems (learning): CUDA programming (currently learning)

Current Development Goals

  • Deepen systems-level proficiency (C + CUDA) to better optimize ML performance paths
  • Strengthen agent evaluation and reliability (grounding, tool safety, automated test harnesses)
  • Understanding of different agentic frameworks
  • Continue building deployment-first ML components usable across cloud and edge environments
  • Typescript for web apps development
  • More about software in general

Links

Pinned Loading

  1. pbirb-mcp pbirb-mcp Public

    MCP server for editing Power BI Report Builder paginated reports (`.rdl`) through Claude or any MCP client. 130+ tools across charts, datasets, layout, parameters, validation. Byte-identical RDL ro…

    Python 2

  2. agents-stocks-psx agents-stocks-psx Public

    Multi-agent AI framework for Pakistan Stock Exchange. Specialized agents collaborate to scrape data, parse financial PDFs, search news, and generate investment recommendations.

    Python 1

  3. multi-agent-system multi-agent-system Public

    The system aims for coordination between specialized agents for inventory management, quote generation, and order fulfillment

    Python

  4. pbi-embedded-app pbi-embedded-app Public

    CSS

  5. digit_detect_classification digit_detect_classification Public

    Python

  6. kalman_filter_object_tracking kalman_filter_object_tracking Public

    Python