AI Scientist – Natural Language, Health Records
Artisight
full-time
Posted on:
Location: 🇺🇸 United States
Visit company websiteJob Level
Mid-LevelSenior
Tech Stack
IoTPyTorchTensorflow
About the role
- Train, fine-tune, and optimize large-scale NLP models for clinical text and health record data.
- Develop methods for extracting insights from structured and unstructured health records, including notes, lab results, imaging reports, and longitudinal patient histories.
- Contribute to the architecture of Artisight’s AI platform, ensuring seamless integration of health record intelligence with other AI modalities (vision, audio, IoT sensors).
- Collaborate closely with AI scientists, engineers, clinicians, and product teams to translate research ideas into production-ready solutions.
- Stay up to date with advances in clinical NLP, generative models, and multimodal AI, and bring these insights into Artisight’s applied research pipeline.
- Share research outcomes through internal discussions, technical reports, and potentially external publications.
Requirements
- M.S. or Ph.D. in computer science, electrical engineering, biomedical informatics, applied AI, machine learning, or a related discipline.
- Demonstrated expertise in clinical NLP or health records AI research, evidenced by open-source contributions or peer-reviewed publications (e.g., NAACL, ACL, NeurIPS, ICML, AMIA, JAMIA).
- Hands-on experience with one or more of: Clinical named entity recognition (NER) and relation extraction; De-identification and privacy-preserving text processing; Clinical summarization, cohort selection, and patient timeline modeling; Predictive modeling for outcomes, risk stratification, or decision support; Integration of structured and unstructured EHR data.
- Proficiency in deep learning techniques such as transformers, diffusion models, self-supervised learning, and sequence-to-sequence architectures.
- Strong coding and experimentation skills with frameworks such as PyTorch or TensorFlow.
- Experience with large-scale training and deployment tools (NVIDIA Triton, ONNX, or similar).
- A collaborative mindset and ability to communicate research findings clearly to both technical and non-technical audiences.
- Nice to haves: Experience with multimodal learning (EHR + imaging + audio + sensor data); Familiarity with federated learning and privacy-preserving AI approaches; Experience deploying AI in real-world healthcare environments; Contributions to open-source health NLP projects (e.g., MedSpaCy, Hugging Face Transformers for clinical text, cTAKES, BioBERT, ClinicalBERT).