Rehan Malik

About

Rehan Malik works in AI engineering, ML & data science and AI automation & agents, based in United States (Verticiti / Reallytics.ai). AI/ML Engineer — building production AI agents, RAG pipelines & LLM systems | daily research publisher | PyTorch, LangChain, AWS | open to work. Public projects on GitHub include Agentic-AI-Workflows (Production AI Agents for enterprise automation — 8+ specialized agents using LangChain, OpenAI function…), Sentinel-AI-Fraud-Detection (Fraud Detection AI Co-Pilot — ensemble XGBoost + Isolation Forest with 650+ features, SHAP explainability,…) and LLM-Fine-Tuning-LoRA (Fine-tuning LLaMA-2, Mistral with LoRA, QLoRA, PEFT — 40% cost reduction vs hosted APIs), mostly written in Python and TypeScript.

Projects 6

• 

  Agentic-AI-Workflows

  Production AI Agents for enterprise automation — 8+ specialized agents using LangChain, OpenAI function calling, and FastAPI. Multi-agent orchestration, tool use, planning loops, guardrails.

  github.com
• 

  Sentinel-AI-Fraud-Detection

  Fraud Detection AI Co-Pilot — ensemble XGBoost + Isolation Forest with 650+ features, SHAP explainability, UMAP clustering, GenAI reports via Amazon Bedrock.

  github.com
• 

  LLM-Fine-Tuning-LoRA

  Fine-tuning LLaMA-2, Mistral with LoRA, QLoRA, PEFT — 40% cost reduction vs hosted APIs. VLLM serving with CUDA optimization on AWS SageMaker.

  github.com
• 

  RAG-Enterprise-Search

  Production RAG pipeline — enterprise knowledge retrieval across 2TB+ data using LangChain, FAISS, ChromaDB, PG-Vector with cross-encoder re-ranking. Deployed on AWS SageMaker.

  github.com
• 

  Voice-AI-Platform

  Real-time voice AI infrastructure — 500+ concurrent calls, WebSockets, Apache Kafka, gRPC/C++ with CUDA. Speech-to-text, sentiment analysis, sales insights.

  github.com
• 

  AI-Engineering-Notes

  AI/ML Engineering Research Notes — Daily technical articles on Agentic AI, RAG, LLM Fine-tuning, MLOps, and production AI systems. Written by Rehan Malik | Senior AI/ML Engineer

  github.com