Applied AI Engineer focused on building robust, scalable Machine Learning infrastructure and fine-tuning domain-specific Large Language Models.
API Uptime
Tokens Processed
Papers Published
Leading a team of 4 engineers to build custom RAG pipelines for enterprise clients. Reduced hallucination rates by 42% through implementation of hybrid search architectures and advanced prompt-chaining.
Optimized model quantization for edge-device deployment. Handled the end-to-end MLOps lifecycle from data ingestion to Kubernetes-based model serving.
A specialized RAG system for legal discovery, capable of analyzing 10k+ pages in seconds with 99.8% citation accuracy.
VIEW SOURCE // _01Low-latency object detection optimized for ARM-based drones. Achieving 60FPS at 4K resolution on-device.
VIEW SOURCE // _02Standardizing the CI/CD/CT loop for maximum reliability.