Skip to content
View Cyr-Ch's full-sized avatar

Block or report Cyr-Ch

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
Cyr-Ch/README.md

๐Ÿ‘‹ Hi, I'm Cyrine

AI Researcher & Founder working at the intersection of foundation models and decision intelligence.

I build large industrial foundation models at BMW for CAD/CAE, and study how to build AI systems that can reason reliably in high-stakes, regulated environments. My broader research interests sit at the intersection of foundation models, world models, agentic systems and evaluation rigor for AI in domains where decisions have real consequences.

Previously co-founded Wattzo, where we built ML forecasting and agentic AI for distributed energy assets. Before that: applied scientist at Microsoft (speech & sign language).

๐ŸŒ Actively collaborating with the Young AI Leaders program under the United Nations ITU's AI for Good initiative, leading projects that apply AI for climate action, sustainability, and positive societal impact.

๐Ÿง  Profiles


๐Ÿ“ซ Contact


"Building intelligent systems that understand, decide, and empower futures." ๐ŸŒ

Pinned Loading

  1. energy-forecasting-bench energy-forecasting-bench Public

    A benchmark for energy forecasting with PatchTST, Autoformer, Informer, and classical baselines using the ETT Dataset

    Python 11 1

  2. Explainable-REC Explainable-REC Public

    Multi-agent system for renewable energy optimization using natural language. Processes energy scenarios, solves MILP optimization problems, and provides interpretable results.

    Python 6

  3. UnbiasedCathode UnbiasedCathode Public

    ๐Ÿ† First Place - MIT Energy & Climate Hack 2023. LLM-powered framework that helps battery researchers optimize material selection and supply chains through natural language questions and Gurobi optiโ€ฆ

    Jupyter Notebook 1

  4. SCA-STGCN SCA-STGCN Public

    Signer-Conditioned Attention ST-GCN with multi-head bias-aware gating

    Python 5

  5. sign-language-translation sign-language-translation Public

    Building a model for Sign Language Translation with I3D features and word-level Transformer

    Python 8

  6. german-dialect-aware-g2p german-dialect-aware-g2p Public

    Dialect-aware grapheme-to-phoneme conversion for German using Transformer + XLM-R. Context-aware, multi-dialect support with CTC+CE training. Built with PyTorch Lightning & Hydra.

    Python 4