Senior Data Scientist – LLM / Clinical NLP

30k - 38k PLN30 000 - 38 000 PLN/ mies./ mies.B2BB2B (netto)

SeniorZdalnie·WarszawaFull-time·B2B

#470490·Dodano 6 dni temu·0

Źródło: justjoin.it

Aplikuj teraz

Tech Stack / Keywords

Python SQLHugging Face transformersBERT / RoBERTaBioBERT / ClinicalBERTLoRA / PEFTRAGLLM

Podsumowanie oferty

Build clinical-data extraction pipelines that turn unstructured clinical notes into structured facts for a US healthcare data company. Evaluate, fine-tune, deploy, and monitor language models used in research-grade data products.

Wymagania

Master's degree or PhD in a quantitative field, such as computer science, machine learning, data science, or biostatistics
Around 5 years of hands-on data science or machine learning work, including taking models to production on messy real-world data
Hands-on NLP experience fine-tuning BERT / RoBERTa-family models, including biomedical or clinical variants such as BioBERT or ClinicalBERT, for named entity recognition, classification, or relation extraction, typically with Hugging Face Transformers
Hands-on experience with generative LLMs, including prompt design and structured outputs, fine-tuning such as LoRA / PEFT, RAG, and evaluating outputs at scale
Rigorous model evaluation skills
Strong Python and SQL skills
Use of AI tools such as Claude and Cursor as a core part of delivery
Fluent English and confidence presenting to cross-functional and non-technical stakeholders

Strongly preferred:

Experience with EHR data or clinical notes, and familiarity with coding systems such as ICD, CPT, or RxNorm

Nice to have:

PySpark and Databricks, including MLflow
Training, serving, and monitoring models on AWS, especially Amazon SageMaker
R or TypeScript
Ophthalmology, urology, or oncology data
Medical imaging data
Real-world evidence studies or peer-reviewed publications

Obowiązki

Build and improve LLM- and transformer-based pipelines to extract structured data from clinical notes, including named entity recognition, text classification, and relation extraction
Evaluate models using gold-standard datasets, error analysis, and metrics trusted by clinicians and researchers
Fine-tune, deploy, and monitor models in production
Work with Medical and Product teams to turn clinical questions into concrete data and model requirements
Present results and trade-offs to technical and non-technical audiences

Benefity

Fully paid licenses for Cursor, Claude Pro, and other tools
Autonomy to own the workflow

Inne informacje

The role is remote within Poland.
Work daily with the client's Product and Medical teams on the US East Coast.

Vecten

Pracodawca

Aplikuj teraz