Building tools that leverage genAI to boost businesses' productivity.

* Architect of backend for LLM-based application. Our backend is built for streaming objects and text from language models, with experimentation in mind. We deploy competing "flows" that chain LLM interaction, database retrieval, and transformations to allow us to search for the best solution for our product.* Prompt/flow engineer. Generally this involves researching the state of the art and implementing the core data flows in our product. The solution space includes various models, model parameters, general techniques (e.g. RAG, finetuning), prompt writing, as well as bespoke flow architectures.

Under contract via John Galt Staffing, Burlington, MA