John Snow LabsRemote
John Snow Labs US-Based Healthcare Data Scientist
United States of America
Full Time
8 hours ago
Visa Sponsor
Key skills
Machine learningNatural language processing (NLP)PythonLarge language models (LLMs)Generative AIDeep learningData science pipelinesData engineering pipelinesClinical data analysisMedical text extractionMedical image analysisOMOPFHIRClinical terminologiesHealthcare domain knowledgePharma domain knowledgeBioinformaticsBiostatisticsSpark NLPModel validation for bias and overfittingAIMachine LearningDeep LearningNLPLLMLarge Language ModelsData EngineeringSparkCommunication
About this role
John Snow Labs is an award-winning AI and NLP company, accelerating progress in data science by providing state-of-the-art software, data, and models. They are seeking a highly skilled Data Scientist to contribute to transformative initiatives within the healthcare industry, focusing on developing and optimizing machine learning models and building robust data pipelines.
Responsibilities:
- Train, fine tune, and enhance LLM & NLP models using the open-source Python library ecosystem. Experience with LLMs, Generative AI, and deep learning is a significant advantage
- Build data science and data engineering pipelines specific to analyzing clinical data, such as extracting information from medical text or images, or integrating uncertain information from multiple medical data sources
- Collaborate with our team on customer-facing projects, utilizing your expertise to create advanced machine learning, deep learning, large language models, and time series forecasting pipelines tailored to address specific business needs
- Ensure models are validated for issues like bias, overfitting, and concept drift to ensure reliability and effectiveness
- Engage directly with customers, requiring strong oral and written communication skills to convey complex technical concepts clearly
Requirements:
- Proven experience in consistently delivering real-world projects covering the key responsibilities. Knowledge that is limited to an academic setting, or to using existing APIs to building applications, is not sufficient for this role
- Hands-on experience with OMOP, FHIR, clinical terminologies, and understanding of the patient journey
- Strong background in healthcare-related fields such as medicine, pharma, bioinformatics, or biostatistics is highly beneficial
- Experience in developing and optimizing machine learning models, specifically within healthcare contexts
- Proficient in training and fine-tuning models, building robust, production-ready model inference pipelines, and conducting comprehensive exploratory data analysis and data enrichment
- Strong oral and written communication skills to convey complex technical concepts clearly
- A PhD in a relevant field is preferred but not required if exceptional experience is demonstrated
- Experience with John Snow Labs' technology stack, such as Spark NLP or the medical language models, is a plus