Connor Shorten
Boston, Massachusetts, United States
Summary
🤩
RockstarConnor Shorten is a research scientist with eight years of engineering experience focused on bridging retrieval and generation for scalable, production-grade systems. He is an active open-source backend contributor to Weaviate — the cloud-native vector database — and to Stanford’s DSPy, where he implemented the WeaviateRM retrieval module and added hybrid search, dependency fixes, and usability improvements. His work includes integrating generative modules and rerankers (Cohere, Ollama), API wiring, refactors, and test coverage, demonstrating a pragmatic mix of research-minded experimentation and production discipline. Connor routinely operates at the intersection of generative feedback loops and retrieval systems, enabling tighter integration between large language models and vector search.
8 years of coding experience
Github Skills (14)
weaviate10
vector-search10
api-doc10
application-integration10
vector-database10
go10
api10
integrate10
dnspy10
python10
integrations10
json9
develop8
grpc8
Programming languages (6)
Github contributions (5)
stanfordnlp/dspy
Aug 2023 - Feb 2025
DSPy: The framework for programming—not prompting—language models
Role in this project:
Back-end Developer
Back-end DeveloperContributions:5 reviews, 36 PRs, 33 pushes in 1 year 5 months
Contributions summary:Connor primarily contributed to the `dspy` repository by implementing and refining the `WeaviateRM` retrieval module. Their work involved setting up the integration with the Weaviate vector database, including initial implementation, correcting errors, and improving functionality. The user addressed issues related to text key customization, and added hybrid search capabilities within the `WeaviateRM` module. They also worked on correcting typos and updating dependencies within the project.
nlpbertknowledgepredictlanguage-models
weaviate/weaviate
Sep 2021 - Oct 2024
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Role in this project:Backend Developer
Backend DeveloperContributions:13 reviews, 17 PRs, 129 pushes in 3 years 2 months
Contributions summary:Connor primarily contributed to the backend of the Weaviate project, focusing on the implementation and configuration of modules. The commits involved integrating the generative-cohere module, including the setup of API keys and the parsing of responses. Furthermore, the user added support for the reranker-cohere module and the Ollama module, demonstrating experience with different generative models. The commits also showcase experience with code refactoring and test creation.
approximate-nearest-neighbor-searchsemantic-search-enginehnswfaultsimilarity-search
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.