Senior Generative AI / Backend Engineer

I am a Senior Generative AI and Backend Engineer focused on designing and delivering production-grade RAG and LLM systems. My work spans document ingestion, hybrid retrieval, reranking, context-aware generation, model evaluation, API delivery, and deployment.

I have led end-to-end AI product development teams and made technical architecture decisions for complex production software. I combine applied machine learning expertise with strong backend engineering practices to create reliable, maintainable AI platforms.

I have hands-on experience fine-tuning and evaluating models through structured MLflow experiments, improving retrieval quality and answer accuracy while making model changes measurable and repeatable. I also build and operate on-premise LLM serving solutions using vLLM.

My background includes deep learning, computer vision, C++, Python, and Autodesk API integrations. I have delivered engineering automation and AI-powered inspection systems that substantially reduced manual work and turnaround times.

I am experienced in inference optimization and production deployment, including moving deep-learning segmentation workloads from Python to C++ for low-latency GPU inference. I enjoy solving performance-critical engineering problems and turning AI research into useful production systems.

I have worked across oil and gas, structural design, engineering automation, and inspection domains. I bring a practical product mindset to AI development, with emphasis on technical quality, measurable outcomes, and cross-disciplinary collaboration.