12 27 43

Nicolay Rusnachenko

nicolay-r

https://nicolayr.com/

AI & ML interests

NLP for Healthcare ⚕️ @BU_Research・PhD in NLP / IR ・Textual Information Retrieval

Recent Activity

posted an update 1 day ago

📢 For those who experimening with large language models in clinical domain, this might be relevant. So far we participated in Task 4 of the ArchEHR-QA 2026 shared task. The task requires aligning answers to patient questions with clinical evidence. Our approach encodes clinical reasoning principles directly into the prompt, evaluated in a zero-shot setting. Results: +2% improvement with ChatGPT-5.2. No measurable gain with Llama-3 70B, indicating the approach benefits larger-scale models. 🌟 Code: https://github.com/nicolay-r/ArchEHR-QA-2026-Task-4-MedEvi-NS 📊 Shared task: https://www.codabench.org/competitions/13528/

posted an update about 1 month ago

📢 I know this space is mosly for sharing works, but in this case I am open to work 💼🇬🇧 I know there are outstanding research labs and teams following this space 🙌 I would genuinely love to learn on ways to contribute, learn from strong lab environments, and help shape ideas into working systems. What I bring (https://nicolayr.com): • Applied NLP & deployment LLM-powered worflows with reasoning for IR (LangChain, LiteLLM) • Architectures Engeneering: Transformers and / or backends (PyTorch, Tensorflow, flaxformer) • End-to-end engineering: Frontend (JS, ReactJS) → Backend REST APIs (FastAPI) / Keycloak → Docker / NGINX → Cloud / MLOps • Domain-specific experience in Healthcare (deploy & handle: DICOM-SR/SEG, NIFTI, databases: ORTHANC, Frontend: OHIF / cornerstone) • Pasion about open-source NLP tooling for handling data (https://github.com/nicolay-r) Would be happy to connect or hear any relevant suggestions on seeking for team 🧩

posted an update about 2 months ago

📢 Who want's to have a quick start for adapting CoT schema for any LLM, this post would be relevant. Excited to share a new version of 🌟 bulk-chain 🌟! Bulk-chain is high-level wrapper over LLM providers for efficient quering LLMs hosted by third-party services. It brings native batching via support of async clients. 🌟 https://github.com/nicolay-r/bulk-chain/tree/master What's new: ☑️ Simplified inference setup The API is now closer to the OpenAI paradigm for toggling streaming. Instead of separate patterns in 1.2.0, now it is possible to simple toggles to enable streaming and async behavior. ☑️ 🛠️ Fixed issues when passing code contain {} blocks ☑️ 🛠️ Async streaming + batching now works properly ☑️ 🛠️ Logging of prompts could be disabled https://github.com/nicolay-r/bulk-chain 🚨 Guys, I am open to work as developer / researcher in AI / NLP / IR in the UK 🇬🇧 🌟 Feel free to support bulk-chain on Github if you like so, or this post. It helps alot!

View all activity

Organizations

None yet

Posts 84

Post

📢 For those who experimening with large language models in clinical domain, this might be relevant. So far we participated in Task 4 of the ArchEHR-QA 2026 shared task. The task requires aligning answers to patient questions with clinical evidence. Our approach encodes clinical reasoning principles directly into the prompt, evaluated in a zero-shot setting.

Results: +2% improvement with ChatGPT-5.2. No measurable gain with Llama-3 70B, indicating the approach benefits larger-scale models.

🌟 Code: https://github.com/nicolay-r/ArchEHR-QA-2026-Task-4-MedEvi-NS
📊 Shared task: https://www.codabench.org/competitions/13528/

Post

318

📢 I know this space is mosly for sharing works, but in this case I am open to work 💼🇬🇧

I know there are outstanding research labs and teams following this space 🙌

I would genuinely love to learn on ways to contribute, learn from strong lab environments, and help shape ideas into working systems.

What I bring (https://nicolayr.com):
• Applied NLP & deployment LLM-powered worflows with reasoning for IR (LangChain, LiteLLM)
• Architectures Engeneering: Transformers and / or backends (PyTorch, Tensorflow, flaxformer)
• End-to-end engineering: Frontend (JS, ReactJS) → Backend REST APIs (FastAPI) / Keycloak → Docker / NGINX → Cloud / MLOps
• Domain-specific experience in Healthcare (deploy & handle: DICOM-SR/SEG, NIFTI, databases: ORTHANC, Frontend: OHIF / cornerstone)
• Pasion about open-source NLP tooling for handling data (https://github.com/nicolay-r)

Would be happy to connect or hear any relevant suggestions on seeking for team 🧩