Work
Adaptive LLM Inference Engine
An academic capstone project exploring efficient LLM inference on resource-constrained devices, with a focus on practical deployment tradeoffs and system behavior.
Projects
Projects
A focused look at the work I build, the experiments I run, and the ideas I explore across software engineering and Generative AI.
From internship contributions to academic systems and local model experiments, each project reflects a different side of the same practice.
Software Engineer Intern at CoAI.Pro
Contributing to AI-powered website generation and web applications while exploring how interfaces can feel clearer, faster, and more helpful.
Three different kinds of work, each shown with its own focus: shipped contribution, academic exploration, and hands-on model experimentation.
Work
Software Engineer Intern at CoAI.Pro
Contributing to AI-powered website generation and web applications, with work that sits close to product thinking and implementation detail.
Experiments
Local LLM Experiments
Hands-on experimentation with Ollama, Qwen, and Llama models, documented through practical evaluation and iterative testing.
Ollama
Qwen
Llama
What ties it together
A common way of thinking
Across every project, the same priorities show up: clarity, practical implementation, and a willingness to explore new tools without losing the user experience.
That mix matters most when software needs to feel technical without becoming difficult to use.
Clarity
Interfaces should explain themselves quickly, even when the underlying system is complex.
Experimentation
New models and tools are most useful when they can be tested against real workflows.
Build quality
Details matter: spacing, hierarchy, and the way each part of a page fits together.
Next
Open to the right kind of conversation
If you want to talk about software, AI products, or a specific build challenge, the next step is simple.