Lead Data Scientist

We are looking for a Lead Data Scientist to own and solve complex data and AI problems that power Arintra's autonomous healthcare systems. This is a hands-on technical leadership role focused on AI/ML, training data, data mining, Gen AI, NLP, and production AI systems.

Responsibilities:

• Own data problem formulation for AI systems, including structuring, labeling, and mining historical decision data, claim outcomes, and domain signals.
• Design training data strategies and build high-quality labeled datasets from real-world healthcare coding decisions and denial outcomes.
• Drive large-scale data mining across complex code and payer spaces to identify rare, high-value patterns.
• Own the architecture and evolution of the core AI platform across real-time inference, batch processing, and model-training pipelines.
• Work across traditional ML, NLP, and Gen AI workloads.
• Architect multi-modal AI systems combining clinical text, structured EHR data, and domain knowledge.
• Evaluate AI tools, platforms, and vendors and drive build-vs-buy decisions.
• Mentor AI engineers across NLP, traditional ML, and Gen AI.
• Lead architecture reviews and establish engineering best practices.
• Collaborate with data engineering, GenAI/NLP, and product teams to align data and model-training strategies with product requirements.

Requirements:

• 8+ years of experience building and deploying production AI/ML systems.
• Strong experience solving complex data problems, beyond model selection or infrastructure.
• Experience working with complex, domain-specific data at scale.
• Strong expertise across NLP, traditional ML, and Gen AI, with production deployments.
• Expert-level proficiency in PyTorch or TensorFlow.
• Experience with model training at scale.
• Proven experience where data quality, labeling strategy, and training data curation were key challenges.
• Experience with cloud-native AI architectures on AWS, Azure, or GCP.
• Experience with Docker and Kubernetes for AI workloads.

Good to Have:

• Experience building self-improving AI systems, active learning pipelines, or feedback-loop architectures.
• Experience with RLHF or outcome-based reward signals.
• Large-scale data mining across high-cardinality feature spaces.
• Experience building autonomous decision engines, recommendation systems, or classification systems that learn from historical outcomes.
• MLOps experience, including CI/CD, model versioning, monitoring, and deployment governance.
• Healthcare AI / medical AI or regulated-industry experience.
• Knowledge of HIPAA, HL7 FHIR, ICD, or CPT.
• Experience with continual learning, domain adaptation, explainable AI, or multimodal AI architectures.