Oluwanifemi Oke's Work | ContraWork by Oluwanifemi OkeOluwanifemi Oke
High-agency AI/ML Engineer architecting and shipping product
A fine-tuned Llama-3 8B model specialized in detecting and patching security vulnerabilities in Python code, trained using Unsloth and PEFT/LoRA, converted to GGUF, and deployed on Hugging Face. A multi-model e-commerce recommendation system utilizing a Variational Autoencoder, SASRec Transformer, and Transformer-DQN reinforcement learning agent, optimized with TFLite and deployed via Docker and FastAPI. An intelligent student success platform built with Flask, LangChain RAG, and an XGBoost performance predictor, backed by Firebase and Cloudinary A financial risk platform combining an LSTM neural network, SHAP explainability, and Llama 3 for automated compliance and risk scoring.