Michael Robinson
Senior AI Engineer at AlphaSense
United States
Summary
🤩
Rockstar🎓
Top SchoolMichael Robinson is a Senior AI Engineer with 14 years of experience building production ML systems across medical, compliance, credit, and consumer lending domains. He combines deep learning, NLP, and computer vision expertise with hands-on engineering in Python, Go, SQL, and shell to deliver models that drive measurable business value. A frequent open-source contributor to prominent projects like LangChain and Unstructured—where he improved document loaders, URL ingestion, and preprocessing bricks—he focuses on making unstructured data pipelines more robust and efficient. His background in chemical and biomolecular engineering from Georgia Tech and early process engineering roles gives him a pragmatic systems perspective that informs scalable model deployment and data automation decisions.
14 years of coding experience
6 years of employment as a software developer
Bachelor of Science (BS) Chemical and Biomolecular Engineering, Bachelor of Science (BS) Chemical and Biomolecular Engineering at Georgia Institute of Technology
Github Skills (29)
transformers10
javascript10
data-pipelines10
python10
machine-learning10
typescript10
ml10
typescript-types10
file-handling10
nlp10
typescripts10
data-pipeline10
testing9
data-engineering9
pandas9
Programming languages (8)
Github contributions (5)
Unstructured-IO/unstructured
Jun 2022 - Feb 2023
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Role in this project:
ML Engineer
ML EngineerContributions:50 releases, 665 reviews, 117 commits in 7 months
Contributions summary:Michael's contributions primarily involve enhancing the unstructured-io/unstructured repository, which focuses on preprocessing pipelines for machine learning. They implemented features for integrating with Label Studio, adding annotation capabilities and error handling to the staging brick. They also contributed to the integration of Hugging Face transformers by developing a staging brick for attention window chunking, creating examples, and adding necessary dependencies. Furthermore, the user added bricks for cleaning text, extracting information from texts, and converting data to a Pandas Dataframe.
docxtrainingnatural-language-processingproductionpreprocessing
langchain-ai/langchain
Feb 2023 - Mar 2023
🦜🔗 Build context-aware reasoning applications
Role in this project:Back-end Developer
Back-end DeveloperContributions:23 reviews, 10 commits, 24 PRs in 1 month
Contributions summary:Michael primarily contributed to the `langchain-ai/langchain` repository by implementing new document loaders and extending existing ones to support a wider range of file types. These contributions included the addition of an `UnstructuredURLLoader` for loading data from URLs, support for `.ppt` files in `UnstructuredPowerPointLoader`, and loaders for MS Word and image files. The user's work involved integrating the `unstructured` library and addressing compatibility issues.
composability
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.