As an Applied AI engineer, I focus on bridging the gap between theoretical AI concepts and their practical, real-world uses. My approach is hands-on: I believe in understanding theory deeply, but only in service of building solutions that deliver tangible results.My foundation in software engineering gave me invaluable experience creating products across diverse organizations. Seeking greater challenges, I transitioned to consulting, where I specialized in delivering software solutions that drove measurable business value.My AI journey began in 2016 with an audited AI course, but it accelerated significantly in 2022 when I enrolled in UT Austin's Post Graduate Program in Artificial Intelligence and Machine Learning. The program not only strengthened my ML fundamentals but also led to speaking engagements at two conferences where I shared insights on AI/ML model training.Following my formal education, I dove deep into self-directed research. A highlight of this period was reimplementing the ReAct white paper in Ruby and developing an educational library focused on Retrieval Augmented Generation, FAISS, and Vector Embeddings – work I later presented at Madison Ruby.Current areas of interest:- Developing robust, production-ready, testable AI applications with Evals.- Helping non AI organizations adopt AI by integrating it with their existing infrastructure. Currently working on establishing best practices for companies using Ruby on Rails.- Creating AI solutions that scratch my own itch and help with personal productivity.I actively contribute to the community through practical use cases on GitHub, technical blog posts, and a newsletter where I share insights from my ongoing work in the field.Blog:https://thedayisntgray.github.io/Newsletter:https://buttondown.com/landon.grayGithub:https://github.com/thedayisntgrayThe best way to reach me is via Linkedin or email: landon.gray@hey.comPlease leave as detailed a description as possible to improve the odds of my getting back to you.Keywords: Hugging Face, NLP, ML, Supervised Learning, Unsupervised Learning, XGBoost, LLMs, RAG, AWS Bedrock, Ruby on Rails, Prompt Engineering, Recommendation Systems, Retrieval Augmented Generation (RAG), Jupyter Notebook, Python, PHP, TypeScript (Angular), JavaScript, Polars, Torch.rb, LibTorch, PyTorch, Transformers, AI Agents, Docker, Generative AI, K-Means Clustering, Data Engineering, Agile, HTML, CSS, JavaScript.