[Remote] Data Scientist

Note: The job is a remote job and is open to candidates in USA. basys.ai is an AI-powered healthcare platform that automates prior authorization and utilization management for health plans using agentic AI workflows and fine-tuned models. The Data Scientist will turn clinical and claims data into statistical and machine learning models, insights, and experiments supporting healthcare workflows such as prior authorization, utilization management, and fraud detection. The role also involves cross-functional collaboration, model deployment and monitoring, mentorship, and healthcare AI thought leadership.

Responsibilities

• Build, validate, and deploy statistical and ML models (classification, time series, NLP, anomaly detection) across diverse healthcare datasets
• Lead experimentation design, hypothesis testing, and model evaluation to inform product strategy
• Contribute to explainability, bias mitigation, and compliance across AI workflows
• Analyze high-volume data including claims, clinical notes, EHR, and policy documents to extract actionable insights
• Define key metrics, build reproducible pipelines, and guide dashboarding with product and operations teams
• Design data labeling and sampling strategies that accelerate model development
• Partner with engineering, ML, product, and clinical teams to define data needs and shape AI-powered workflows
• Translate complex findings into clear, compelling narratives for internal and external stakeholders
• Work closely with DevOps and backend teams to ensure scalable deployment and monitoring of models
• Mentor junior data scientists and contribute to team knowledge sharing
• Keep up with emerging trends in healthcare AI, generative models, and policy-focused analytics
• Represent basys.ai in research, publications, or external stakeholder conversations as needed

Skills

• Based in the United States for at least more than 3+ years, with eligibility to work full-time
• 3-4+ years of experience in data science or advanced analytics roles, with a strong record of ownership and impact
• Strong command of Python, SQL, and data libraries (e.g., Pandas, NumPy, Scikit-learn, Statsmodels)
• Experience designing and deploying production-grade models in healthcare or highly regulated environments
• Proficiency in experimental design, A/B testing, and statistical analysis
• Excellent communication skills, including writing clear documentation and presenting findings
• Experience with healthcare data (claims, EHR, clinical notes) and familiarity with HL7, FHIR, ICD-10, CPT, etc
• Background in NLP, LLM fine-tuning, or transformer-based architectures
• Exposure to fraud/waste/abuse detection, prior authorization automation, or policy alignment
• Comfort working with BI tools (Metabase, Tableau, Looker) and cloud data platforms (AWS, Snowflake, Redshift)
• Strong curiosity, product intuition, and a desire to work on meaningful, complex challenges in healthcare

Benefits

• Equity
• Collaboration with a mission-driven team and world-class partners from Harvard, MIT, Mayo Clinic, and CMS
• Flexible, remote-first work setup with a focus on outcomes over hours
• A fast-moving startup environment with real-world clinical and policy impact

Company Overview