Rehan Malik

Profile README

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

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

Full RLHF pipeline — SFT, reward modeling, PPO with KL divergence constraints. 68% win rate vs SFT baseline, 96% safety compliance.

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

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