Data Scientist Specialized in NLP & LLM for Healthcare

About Norstella At Norstella, we are driven by a vital mission: to accelerate the availability of life-saving therapies to patients who need them most. Though founded in 2022, our legacy extends back to 1939, bringing together top-tier brands to support clients through the complex drug development lifecycle. We partner with innovative organizations like Citeline, Evaluate, MMIT, Panalgo, and The Dedham Group, each contributing essential insights for strategic decision-making. Join Our Team If you are passionate about utilizing your expertise in Natural Language Processing (NLP) and large language models (LLMs) to make a significant impact in healthcare, we invite you to apply for the NLP & LLM Data Scientist position with our Real World Data (RWD) team. This role focuses on transforming unstructured medical data into actionable insights that drive faster drug development. Key Responsibilities: Utilize NLP techniques and open-source LLMs like LLama2, Mixtral, and BERT to analyze and interpret unstructured medical data from sources such as Electronic Health Records (EHRs) and lab reports. Collaborate with clinical and data scientists to develop efficient NLP models tailored for healthcare applications. Engage in data cleaning, preprocessing, and validation to ensure the accuracy and reliability of NLP findings. Effectively communicate data insights to stakeholders, ensuring transparency and clarity in presentations. Qualifications: Master's or Ph.D. degree in a relevant field such as Computational Biology, Computer Science, or Data Science. At least 2 years of experience in analyzing EHRs, lab results, or genetic tests. Demonstrated expertise in NLP techniques (NER, text summarization, topic modeling) applied within healthcare. Hands-on experience (1+ years) working with LLMs, including prompt engineering and model fine-tuning. Proficiency in Python and SQL, along with experience in NLP libraries and deep learning frameworks. Familiarity with AWS cloud services and managing large datasets. Strong analytical mind with a detail-oriented approach to solving complex problems. Excellent communication skills, capable of presenting intricate data to non-technical audiences. Preferred Qualifications: Experience managing Protected Health Information (PHI) in compliance with healthcare regulations like HIPAA. Knowledge of healthcare standards (ICD-10, CPT, LOINC, SNOMED CT). Experience with Retrieval-Augmented Generation (RAG) and related data query techniques. Benefits: Medical and prescription drug coverage Health savings and flexible spending accounts Dental and vision plans 401k retirement plan Short- and long-term disability coverage Paid parental leave Generous paid time off policies Our Principles: Embrace Boldness and Passion in our mission. Uphold Integrity and Transparency in all endeavors. Foster Kindness, Empathy, and open communication. Demonstrate Resilience and Perseverance through challenges. Commit to Learning with Humility and Gratitude. The expected base salary for this role ranges from $140,000 to $200,000, with discretionary bonuses available. We are dedicated to fostering an inclusive and diverse workplace where every individual is valued for their unique contributions. Norstella is an equal opportunity employer, welcoming applications from all qualified candidates regardless of their background.