Senior Machine Learning Scientist, NLP

Summary

Join Tempus's research and development team as a Senior Machine Learning Scientist to develop cutting-edge natural language processing models and LLMs for healthcare applications. You will play a crucial role in optimizing clinical workflows, improving clinical trial matching, and advancing medical research. This position requires developing and deploying machine learning models for various tasks, including information extraction, relation extraction, and clinical prediction. Collaboration with cross-functional teams and healthcare professionals is essential. The role demands staying current with healthcare regulations and AI trends, publishing research findings, and collaborating with external partners. This is an exciting opportunity to leverage AI to revolutionize healthcare and improve patient outcomes.

Requirements

• PhD or Master's degree with 3+ years of experience or Bachelor's degree with 5+ years of experience in a quantitative discipline such as computer science, artificial intelligence, machine learning, statistics, natural language processing, computational linguistics, information retrieval, computational biology, bioinformatics, applied mathematics, physics, or a related field
• Strong collaboration, communication, and influencing skills
• Strong track record of publications, patents, and/or launched products in AI using NLP or LLMs
• Solid knowledge of machine learning concepts, including deep learning, transformer models, optimization algorithms, and regularization techniques
• Proficiency in AI programming languages and frameworks such as Python, PyTorch, TensorFlow, Keras, Pandas, scikit-learn, spaCy, and NLTK
• Strong software engineering and programming skills using Python, Linux, and SQL
• Strong bias to action and appetite for high-risk, high-gain projects

Responsibilities

• Develop innovative and practical natural language processing models and LLM agents for precision medicine
• Research, develop, train, test, deploy, monitor, and improve machine learning models and agents for information extraction, relation extraction, information retrieval, question answering, text classification, summarization, and clinical prediction
• Work with unstructured clinical notes and reports, structured electronic health record (EHR) data, imaging data, and molecular (DNA and RNA sequencing) data
• Continuously explore and evaluate new technologies and methodologies to enhance the technical capabilities of our team
• Contribute to thought leadership and continue to develop and apply up-to-date knowledge of AI trends
• Design and conduct experiments to evaluate the performance and effectiveness of NLP models and LLM agents in healthcare settings
• Collaborate with business, product, and other teams to develop the vision, business case, requirements, roadmap, and plan for AI-powered products
• Collaborate closely with healthcare professionals, data scientists, software engineers, and product managers to gain insights into real-world healthcare challenges and develop practical solutions
• Work closely with engineering teams to integrate your models and agents into healthcare platforms, systems, and applications. Ensure scalability, efficiency, and robustness of deployed solutions
• Stay up to date with healthcare regulations, privacy laws, and ethical considerations relevant to the development and deployment of AI in healthcare. Ensure compliance with HIPAA, GDPR, and other applicable standards throughout the development process
• Stay actively involved in the healthcare and AI research communities. Attend relevant conferences, workshops, and seminars. Publish research findings in important scientific venues
• Collaborate with university and industry partners to advance the state of the art in AI for healthcare. Establish and drive research opportunities and collaboration with partner organizations

Preferred Qualifications

• Experience building production models and agents for information extraction, relation extraction, information retrieval, question answering, text classification, summarization, and/or clinical prediction
• Experience with LLM frameworks such as LangChain, LangGraph, LlamaIndex, and Semantic Kernel
• Experience with embeddings and multimodal fusion
• Experience in the healthcare domain, especially in oncology
• Experience working with clinical, molecular, and imaging data
• Experience with medical ontologies and controlled vocabularies such as UMLS, SNOMED CT, MeSH, NCI Thesaurus, RxNorm, and HGNC

Benefits

Tempus offers a full range of benefits, which may include incentive compensation, restricted stock units, medical and other benefits, depending on the position