Skip to content
View xmassmx's full-sized avatar

Block or report xmassmx

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
xmassmx/README.md

Hi, I'm Muhammad Abdullah Shafat Mulkana

Head of AI & Founding Engineer | Multi-agent systems | LLM infrastructure | Production GenAI

Leading AI engineering at Wubble AI - real-time multimodal audio generation (music, vocals, SFX) and agentic workflows at scale.

LinkedIn Medium Substack


What I build

Agentic & LLM systems
  • LangGraph multi-agent systems (HITL, routing, tool-calling)
  • RAG and LLM deployment across major model providers
  • MCP dev tooling (langmcp)
Multimodal & real-time AI
  • Real-time audio generation (music, vocals, SFX)
  • Voice AI (streaming STT -> LLM -> TTS)
  • Transformer serving on Kubernetes
Production infrastructure
  • Multi-cloud GPU stacks (AWS/GCP) with routing and autoscaling
  • Event-driven microservices (FastAPI, Pub/Sub, Redis, PostgreSQL)
  • MLOps: CI/CD, IaC, versioning, monitoring
Applied ML & vision
  • Computer vision and real-time detection (e.g. YOLOv8)
  • OCR and document pipelines
  • NLP/CV research (captioning, generative models)
---

Tech stack

Languages and backends

Python FastAPI Flask TypeScript SQL MATLAB

ML / AI

PyTorch TensorFlow Keras LangChain LangGraph Transformers CrewAI ONNX

LoRA fine-tuning | instruction tuning | RAG | prompt engineering | model optimization

Agents and LLM ops

MCP Weaviate Chroma FAISS pgvector

Multi-agent orchestration | HITL workflows | tool-calling | agentic AI | semantic search

Cloud and infrastructure

AWS GCP Kubernetes Docker Redis PostgreSQL Elasticsearch Firebase Databricks

AWS: EC2 | Lambda | S3 | SageMaker
GCP: Cloud Run | Cloud Functions | Pub/Sub | GKE | Vertex AI | Cloud Storage

MLOps and delivery

GitHub Actions GitLab CI Docker Compose GitOps

Infrastructure-as-code | model versioning

Domains

Generative AI LLMs Computer Vision NLP Diffusion Object Detection


Background

B.Sc. Electrical and Electronics Engineering, Bilkent University (Honors, Cum Laude).

Previously: LAYMARK (multi-agent and Voice AI) | Simply Complex Lab @ National Nanotechnology Research Center (deep learning for microscopy) | applied ML across CV, OCR, and generative modeling.


Connect

Pinned Loading

  1. langmcp langmcp Public

    A MCP server that will connect with LangChain Checkpointers, Memory Stores, Vectorstores to aid in monitoring and observability during development of AI Applications

    Python 2

  2. Image-Captioning Image-Captioning Public

    Image Captioning using encoder-decoder and attention

    Python 1

  3. smart-pots-app smart-pots-app Public

    Smart Pots System - Final Year Project

    Dart 2

  4. RAG RAG Public

    Python 1

  5. mcp mcp Public

    Python