Charles Pierse
Director Of Innovation Labs
Dublin, Ireland
Summary
🤩
Rockstar🎓
Top SchoolCharles Pierse is a Director of Innovation Labs and machine learning engineer with 11 years’ experience building scalable NLP, search, recommendation, and knowledge-graph systems. He designs production-grade ML architectures and retrieval pipelines—having led search and conversational AI products that combine embeddings, LLMs, and custom agent logic to validate and format answers. A strong open-source advocate, Charles authored transformers-interpret (900+ stars, 200k+ downloads) and contributed to Weaviate’s HNSW vector search internals, improving commit-log compaction and deserialization performance. He blends hands-on backend engineering with product-led thinking, managing Kubernetes and AWS infrastructure to deliver reliable, user-focused AI services. With a BSc in Computer Science and an MSc in Literature and Modernity, he brings a rare mix of technical depth and humanities-informed perspective on language and explainability. Based in Dublin, he thrives at the intersection of model interpretability, scalable systems, and practical AI products.
11 years of coding experience
6 years of employment as a software developer
Master of Science (MSc) Literature and Modernity , Master of Science (MSc) Literature and Modernity at The University of EdinburghLeaving Certificate, Leaving Certificate at Rockwell CollegeBachelor of Science (BSc) Computer Science, Bachelor of Science (BSc) Computer Science at University College Dublin
English, French
Github Skills (18)
transformers10
vector-search10
pytorch10
xai10
python10
machine-learning10
data-serialization10
vector-database10
serialization10
deserialization10
explainable-artificial-intelligence10
go10
data-structure9
deep-learning9
nlp9
Programming languages (8)
Github contributions (5)
cdpierse/transformers-interpret
May 2020 - Jan 2023
Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
Role in this project:
ML Engineer
ML EngineerContributions:13 releases, 18 reviews, 246 commits in 2 years 8 months
Contributions summary:Charles primarily contributed to the development of an explainability tool for Transformer models within the `transformers-interpret` repository. They added foundational code for explainers, including base classes, signatures, and abstract methods. Their contributions involved the creation of input reference pairs and the implementation of attribution methods, demonstrating a focus on interpreting and visualizing machine learning models.
bertnatural-language-processingexplainabilitytransformerslines
weaviate/weaviate
Jul 2021 - Aug 2021
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:Back-end Developer
Back-end DeveloperContributions:7 reviews, 16 commits, 8 PRs in 16 days
Contributions summary:Charles primarily contributed to the `hnsw` vector search implementation, a core component of the Weaviate vector database. They worked on refactoring and optimizing the commit log functionality, creating a `MemoryCondensor2` and `Deserializer2` to handle commit log compaction and reduce memory allocations. These changes involved modifying code related to data serialization, deserialization, and index restoration, improving efficiency. The user also integrated the new deserializer and condensor into the Weaviate startup and maintenance procedures.
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.