ML Scientist (Research)

Key Responsibilities

• Develop and optimize models for medical speech recognition across 200+ specialties
• Research and implement clinical NLP pipelines for automated E&M coding and ICD-10 classification
• Design and evaluate note quality scoring systems using LLMs and structured clinical rubrics
• Create specialty-specific language models (e.g., gastroenterology, dermatology, emerging markets)
• Design and prototype agentic AI systems for clinical decision support and documentation assistance
• Optimize models for real-time inference with sub-200ms latency requirements
• Build rigorous evaluation frameworks for clinical accuracy, MDM validation, and MIPS quality measure compliance
• Collaborate with clinical experts to validate outputs and ensure alignment with regulatory and documentation standards
• Transition research findings into production-ready solutions in partnership with applied ML and platform engineering teams

Required Qualifications

• 5+ years of experience in machine learning research or ML engineering with a focus on NLP and/or speech recognition
• Strong expertise in PyTorch or TensorFlow
• Deep experience with transformer architectures and large language models
• Proven ability to design and build production-grade ML pipelines at scale
• Strong understanding of model optimization techniques (quantization, distillation, pruning)
• Experience working with cloud ML platforms (AWS SageMaker, GCP Vertex AI, or equivalent)
• Master’s or PhD in Computer Science, Machine Learning, or related field

Preferred Qualifications

• Experience in healthcare AI or clinical NLP
• Familiarity with medical terminology and clinical documentation workflows
• Experience with speech recognition systems (Whisper, Conformer architectures, etc.)
• Knowledge of medical coding systems (CPT, ICD-10, SNOMED)
• Publications in leading ML/NLP conferences
• Experience deploying models in regulated environments (e.g., GovCloud, HIPAA-compliant systems)

Technical Environment

• Python, PyTorch, TensorFlow
• Transformer-based LLM architectures
• Triton Inference Server (AWS GovCloud deployments)
• AWS (SageMaker, EKS, S3, Lambda)
• Real-time inference systems with strict latency constraints (
• Clinical data pipelines and structured evaluation frameworks

Compensation & Benefits

• Meaningful equity compensation
• Unlimited PTO
• Premium health, dental, and vision coverage
• 401(k) plan