About Us:
- We are a growing healthcare technology organization focused on improving access to care, strengthening clinical operations, and reducing administrative burden through thoughtful use of technology, data, and artificial intelligence.
- Our work supports scalable, team-based care delivery models and helps clinical, operational, and business teams make better, faster, and more informed decisions.
- We are building practical AI and machine learning solutions that are reliable, secure, clinically useful, and designed for use in regulated healthcare environments.
About the Role:
- We are seeking a Senior AI/ML Engineer to help design, build, train, evaluate, and deploy machine learning and natural language processing systems that support healthcare operations, clinical documentation, risk adjustment, care-gap identification, and population health analytics.
- This is a hands-on senior individual contributor role with ownership across the full machine learning lifecycle.
- You will work from problem definition and data preparation through model development, evaluation, deployment, monitoring, and continuous improvement.
- The ideal candidate has strong experience with applied machine learning, clinical or healthcare NLP, large language models, MLOps, and responsible AI practices.
- This role will work closely with technology, product, analytics, clinical operations, quality, and revenue cycle stakeholders to translate real-world healthcare needs into practical AI/ML solutions.
- This is a full-time, remote position.
- Candidates should be able to maintain regular overlap with U.S. Eastern Time business hours to support collaboration with U.S.-based teams.
Key Responsibilities:
Machine Learning Model Development:
- Design, implement, train, and evaluate machine learning and deep learning models for healthcare use cases.
- Develop supervised, semi-supervised, and self-supervised learning approaches where appropriate.
- Fine-tune large language models and transformer-based architectures for healthcare-specific tasks such as document classification, summarization, information extraction, and clinical text understanding.
- Apply modern training techniques such as instruction tuning, parameter-efficient fine-tuning, LoRA, QLoRA, and related methods.
- Evaluate model performance using appropriate benchmarks, validation approaches, and real-world feedback loops.
Clinical NLP and Information Extraction:
- Build NLP pipelines for unstructured and semi-structured healthcare text, including encounter notes, care assessments, prior authorization documents, discharge summaries, and other clinical documentation.
- Develop models and pipelines for named entity recognition, relation extraction, classification, summarization, assertion detection, and negation or uncertainty detection.
- Map extracted information to relevant clinical and coding standards where applicable, including ICD-10-CM, HCC categories, SNOMED CT, RxNorm, CPT, LOINC, or related healthcare terminology systems.
Hemisphere Analytics and Risk Adjustment:
- Develop predictive models that support healthcare operations, risk adjustment, care-gap identification, quality improvement, and population health initiatives.
- Build models and analytics that help identify relevant clinical information, improve coding accuracy, support quality measures, and surface actionable insights for care teams and operational users.
- Design feedback loops and active learning approaches to improve model performance over time.
LLM Integration and Applied AI Systems:
- Design and implement AI systems that use large language models as part of practical healthcare workflows.
- Build retrieval-augmented generation pipelines, structured extraction tools, embedding strategies, and vector search solutions.
- Evaluate foundation models, embedding models, vector databases, and orchestration approaches for healthcare use cases.
- Ensure AI systems are designed for explainability, auditability, reliability, and responsible use in regulated environments.
Data Engineering and MLOps:
- Own or contribute to data pipelines from source systems through feature engineering, dataset curation, training, evaluation, and deployment.
- Work with structured and unstructured healthcare data, including EHR data, claims data, FHIR APIs, HL7 feeds, and related healthcare data sources.
- Build scalable workflows using tools such as Spark, dbt, Airflow, or similar technologies.
- Deploy and operate models using cloud-native MLOps practices, including containerized inference, model registries, experiment tracking, drift monitoring, CI/CD, and automated retraining pipelines.
- Maintain model documentation, versioning, performance dashboards, monitoring, and retraining criteria.
Collaboration and Technical Leadership:
- Partner with engineering, product, clinical, analytics, quality, and business stakeholders to understand priorities and translate them into AI/ML solutions.
- Communicate model behavior, limitations, tradeoffs, and performance clearly to both technical and non-technical audiences.
- Mentor other engineers or data scientists through technical reviews, pair work, documentation, and knowledge sharing.
- Stay current with applied machine learning, healthcare AI, clinical NLP, and responsible AI research and identify opportunities to apply relevant advances.
Required Qualifications:
- Bachelor’s degree in Computer Science, Machine Learning, Statistics, Computational Linguistics, Data Science, or a related technical field, or equivalent professional experience.
- 2+ years of professional experience in applied machine learning, AI engineering, data science, or a related role.
- Demonstrated experience deploying machine learning models or AI systems into production environments.
- Hands-on experience with large language models and transformer-based architectures such as BERT, RoBERTa, T5, LLaMA, Mistral, GPT variants, or similar models.
- Strong NLP fundamentals, including tokenization, embeddings, sequence labeling, text classification, information extraction, summarization, and generative modeling.
- Strong Python skills and experience with ML/NLP libraries such as PyTorch, TensorFlow, JAX, Hugging Face Transformers, spaCy, scikit-learn, or similar tools.
- Experience with parameter-efficient fine-tuning methods such as LoRA, QLoRA, adapters, or related approaches.
- Experience building retrieval-augmented generation pipelines, vector search systems, embedding workflows, or domain-specific retrieval solutions.
- Strong understanding of ML evaluation practices, including train/dev/test splits, cross-validation, calibration, bias and fairness evaluation, and statistical testing.
- Experience with MLOps tooling such as MLflow, Weights & Biases, model registries, Docker, Kubernetes, CI/CD pipelines, or similar tools.
- Working knowledge of healthcare privacy, security, compliance, and data governance considerations.
- Excellent written and verbal communication skills in English.
- Ability to maintain at least 4 hours of daily overlap with U.S. Eastern Time business hours.
Preferred Qualifications:
- Experience applying NLP or machine learning to clinical text, EHR data, healthcare claims data, or other healthcare datasets.
- Familiarity with healthcare NLP frameworks, clinical ontologies, or medical terminology systems.
- Experience with clinical coding standards such as ICD-10-CM, CPT, HCC categories, SNOMED CT, RxNorm, or LOINC.
- Working knowledge of Medicare Advantage risk adjustment, HCC/RAF scoring, HEDIS, STARS, or related healthcare quality programs.
- Experience building or consuming FHIR R4 APIs or processing HL7 clinical data formats.
- Experience with clinical document understanding, including section detection, note summarization, problem list generation, CDI tools, or documentation improvement workflows.
- Familiarity with privacy-preserving machine learning techniques, de-identification pipelines, federated learning, or differential privacy.
- Published research, conference contributions, open-source work, or technical writing in NLP, clinical AI, healthcare analytics, or applied machine learning.
- Experience in a startup, high-growth, or distributed team environment.
What Success Looks Like:
- Production AI and ML systems are reliable, measurable, monitored, and aligned with business and clinical objectives.
- NLP pipelines extract useful, accurate, and actionable information from clinical documentation and healthcare data.
- LLM-powered tools improve operational efficiency while maintaining appropriate safeguards, explainability, and oversight.
- Model development follows rigorous evaluation standards, with clear documentation, monitoring, and retraining criteria.
- Privacy, security, and compliance requirements are considered throughout the data, model, and deployment lifecycle.
- Clinical, operational, and business stakeholders trust the outputs of AI/ML systems and understand their appropriate use.
- The engineering team’s ML practices become more mature, reproducible, and scalable over time.
- Communication with U.S.-based teams is proactive, clear, and aligned with delivery priorities.
Compensation and Benefits:
- Employment Type: Full-time.
- Work Location: Remote.
- Compensation: Competitive salary based on experience, qualifications, and location.
- Bonus Eligibility: Performance-based bonus opportunities may be available based on company and individual performance.
- Benefits: Benefits are provided in accordance with applicable local requirements and company benefit plans.
Additional Information:
- We are a growing organization, and this role may evolve as our AI/ML capabilities expand.
- Candidates with strong technical ownership, collaboration skills, and leadership potential are encouraged to apply.
