San Jose, California, United States
In this role, I research and evaluate AI/ML tools to enhance the productivity and efficiency of my team. I focus on applying technologies such as LLMs, embeddings, and agentic retrieval augmented generation to workflows within our organization. My work involves comparing commercial AI platforms and building prototypes that streamline workflows while meeting security and performance needs.
I work with my team to identify bottlenecks and develop solutions that integrate with internal tools. This includes experimenting with chatbot frameworks, embedding models, and secure vector databases. Through this work, I’ve gained hands on experience with prompt engineering, cloud-based AI hosting, and best practices in responsible AI tool adoption.